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

    Neuronpedia

    INDEX
    Explanations

    sentences with intensifiers followed by adjectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating extreme conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redes
    -0.78
    aho
    -0.64
    zman
    -0.64
    ACC
    -0.61
    YS
    -0.59
    áµ
    -0.57
     conduc
    -0.56
     aft
    -0.56
    UG
    -0.55
    enfranch
    -0.55
    POSITIVE LOGITS
     they
    0.88
     it
    0.85
     nobody
    0.80
    ruciating
    0.75
     even
    0.72
     we
    0.69
     hardly
    0.68
    eday
    0.67
    terday
    0.67
    soever
    0.65
    Act Density 0.090%

    No Known Activations