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

    Neuronpedia

    INDEX
    Explanations

    mentions of operating metrics and performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reap
    -0.15
     balk
    -0.15
    isher
    -0.15
    ï
    -0.15
    254
    -0.15
     _
    -0.14
    ouver
    -0.14
     Dict
    -0.14
    orama
    -0.14
    ey
    -0.14
    POSITIVE LOGITS
    ÅĻeh
    0.16
    ãĥĥãĤ°
    0.15
    æĥij
    0.15
    виÑĩай
    0.15
    rosso
    0.15
    pios
    0.14
    arma
    0.14
    SAME
    0.14
    iyon
    0.14
    utton
    0.14
    Act Density 0.006%

    No Known Activations