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

    Neuronpedia

    INDEX
    Explanations

    negations and conditional phrases

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

    Follows "to" or a single-letter token

    np_acts-logits-general · gemini-2.0-flash

    verbs of being or occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.81
    Portail
    -0.74
     myſelf
    -0.73
     chofe
    -0.72
    ſelf
    -0.70
     leaſt
    -0.70
     ſind
    -0.69
     pleaſure
    -0.69
     uſe
    -0.69
     onAnimation
    -0.69
    POSITIVE LOGITS
     consist
    0.81
     occur
    0.79
     entail
    0.68
     serve
    0.67
     happen
    0.65
     contain
    0.64
     ocur
    0.64
     constitute
    0.64
     arise
    0.63
     comprise
    0.62
    Act Density 0.865%

    No Known Activations