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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment towards individuals or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ«ãĥī
    -0.16
    obic
    -0.16
    elsey
    -0.15
     privilege
    -0.15
    ULL
    -0.15
    ãĤ¯ãĥŃ
    -0.15
    tera
    -0.14
     اÙĦÙħÙĦ
    -0.14
    stav
    -0.14
     extr
    -0.14
    POSITIVE LOGITS
     guts
    0.19
    ays
    0.17
    ograd
    0.15
    ermann
    0.15
    _NT
    0.15
    astos
    0.15
    atos
    0.15
    arkin
    0.14
    KT
    0.14
    enty
    0.14
    Act Density 0.110%

    No Known Activations