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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and their usage in sentences

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

    "and" followed by positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    conjuncting descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ErrIntOverflow
    -0.69
    exitRule
    -0.66
    prefixer
    -0.62
    Autoritní
    -0.56
    ckeditor
    -0.55
    afficheront
    -0.55
     Мексичка
    -0.54
    ulisan
    -0.52
    Filmografie
    -0.52
    ymce
    -0.50
    POSITIVE LOGITS
    何より
    0.75
     definitely
    0.70
     surtout
    0.66
     natuurlijk
    0.64
     Definitely
    0.61
     natürlich
    0.61
     уж
    0.60
     importantly
    0.58
     ovviamente
    0.58
     plenty
    0.57
    Act Density 0.081%

    No Known Activations