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

    Neuronpedia

    INDEX
    Explanations

    words indicating a conditional or hypothetical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Приятного
    -0.59
    存于互联网档案馆
    -0.59
     Autó
    -0.57
    glBegin
    -0.57
    mazoo
    -0.54
     stalk
    -0.53
     drame
    -0.53
    ýš
    -0.52
    entibus
    -0.52
     AttributeSet
    -0.52
    POSITIVE LOGITS
     ohnehin
    0.74
    licherweise
    0.70
    tdessen
    0.69
     sowieso
    0.68
     pourtant
    0.67
     offenbar
    0.67
     gynhyrchwyd
    0.66
    eraard
    0.66
     hefyd
    0.66
    intem
    0.66
    Act Density 0.368%

    No Known Activations