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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conclusions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    říklad
    -0.55
    stuhl
    -0.53
     plainte
    -0.53
     _('
    -0.53
    WSGI
    -0.53
     CURIAM
    -0.52
     pérd
    -0.51
     InkWell
    -0.51
    führ
    -0.51
    /*:
    -0.50
    POSITIVE LOGITS
     being
    1.12
     having
    0.97
     needing
    0.92
     looking
    0.79
    being
    0.77
     doing
    0.76
     giving
    0.73
     wanting
    0.73
     becoming
    0.71
     BEING
    0.71
    Act Density 0.097%

    No Known Activations