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

    Neuronpedia

    INDEX
    Explanations

    words related to determination, passion, conviction, and activism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    artifacts
    -0.94
    ĸļ
    -0.94
    ©¶æ
    -0.83
    earable
    -0.81
    mbuds
    -0.79
    ovember
    -0.77
    ICAN
    -0.77
    Ĥİ
    -0.75
     disadvant
    -0.75
     Surv
    -0.74
    POSITIVE LOGITS
    ness
    1.26
    ly
    1.22
     enough
    0.97
     pursuit
    0.93
     contributors
    0.88
    ling
    0.88
     eye
    0.86
     reader
    0.82
    lings
    0.82
     onlook
    0.82
    Act Density 2.542%

    No Known Activations