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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and references to actions that rely on specific circumstances or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Egli
    -0.80
     Eſ
    -0.78
     Monfieur
    -0.75
     raiſ
    -0.71
     Efq
    -0.70
     ſtate
    -0.69
     〈
    -0.68
     ―――――
    -0.67
     unſ
    -0.66
     Jefus
    -0.66
    POSITIVE LOGITS
     then
    0.76
     it
    0.70
     shouldn
    0.68
    ⓧ
    0.64
     instead
    0.62
     you
    0.60
    __':
    0.59
     should
    0.58
    0.58
     don
    0.57
    Act Density 0.270%

    No Known Activations