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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apparti
    -0.67
    ValueStyle
    -0.65
    styleable
    -0.63
     tros
    -0.63
     enfans
    -0.60
     batalha
    -0.59
     casó
    -0.59
     '{@
    -0.59
     religieuses
    -0.59
    Література
    -0.59
    POSITIVE LOGITS
     caused
    0.86
     eventual
    0.83
     resulting
    0.83
     resulted
    0.83
     increased
    0.83
     causes
    0.79
    caused
    0.77
     a
    0.76
     causing
    0.75
     terjadinya
    0.74
    Act Density 0.398%

    No Known Activations