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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts indicating actions and potential consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wnętr
    -0.80
     yawn
    -0.78
    Дереккөздер
    -0.76
     parapet
    -0.74
     desertion
    -0.73
     uſe
    -0.73
    EXISTS
    -0.72
     Cæsar
    -0.71
     solubility
    -0.71
     blowout
    -0.70
    POSITIVE LOGITS
     getting
    0.92
     taking
    0.87
     doing
    0.84
     making
    0.84
    ating
    0.80
     putting
    0.79
     paying
    0.79
     working
    0.78
     keeping
    0.77
    lieving
    0.77
    Act Density 0.345%

    No Known Activations