Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to abilities and skills, specifically in a context of adaptability or transitioning between roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows specific conjunctions/transition words

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Надо
    -1.05
     freilich
    -1.02
     daß
    -1.00
     jedenfalls
    -0.98
    Надо
    -0.96
     variously
    -0.90
    Herzliche
    -0.90
    FWIW
    -0.87
    けっこう
    -0.85
     offenbar
    -0.85
    POSITIVE LOGITS
     hierbei
    0.82
     possu
    0.77
     anteriormente
    0.76
     данного
    0.73
     demnach
    0.72
     entirety
    0.72
    casted
    0.71
    ⅗
    0.70
    Lastly
    0.70
    rekli
    0.69
    Act Density 1.070%

    No Known Activations