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

    Neuronpedia

    INDEX
    Explanations

    concepts surrounding individual choices and personal autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cref
    -0.57
    pitaux
    -0.56
    __.__
    -0.53
     CreateTagHelper
    -0.53
     Besoin
    -0.51
    makeText
    -0.49
    ]}>
    -0.49
    Executives
    -0.48
     ligiloj
    -0.47
     TAMBIÉN
    -0.47
    POSITIVE LOGITS
    CHOICE
    0.65
     choice
    0.62
    choice
    0.62
     sumpay
    0.59
     décision
    0.57
     Cæsar
    0.55
     decides
    0.54
     Shakspeare
    0.54
     individuale
    0.54
     friv
    0.54
    Act Density 0.252%

    No Known Activations