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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.03
     houſe
    -0.97
     greateſt
    -0.96
     ſtate
    -0.95
     beſt
    -0.95
     faſt
    -0.95
     myſelf
    -0.94
     Roskov
    -0.93
     pleaſure
    -0.92
     itſelf
    -0.92
    POSITIVE LOGITS
     a
    0.59
     
    0.56
     Long
    0.51
    Kaieteur
    0.50
     B
    0.49
     for
    0.49
     K
    0.49
     to
    0.48
     also
    0.48
     on
    0.48
    Act Density 0.147%

    No Known Activations