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

    Neuronpedia

    INDEX
    Explanations

    information related to self-improvement and personal development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     câte
    -0.86
     gând
    -0.86
     deschis
    -0.84
     argint
    -0.81
     obicei
    -0.81
     stället
    -0.79
     picioare
    -0.79
     viață
    -0.79
     culoare
    -0.78
     acoper
    -0.78
    POSITIVE LOGITS
     decid
    0.69
     mak
    0.69
     contribut
    0.68
     retur
    0.68
     provid
    0.66
     repla
    0.66
     represen
    0.66
     starte
    0.66
     arriv
    0.65
     conti
    0.65
    Act Density 0.642%

    No Known Activations