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

    Neuronpedia

    INDEX
    Explanations

    recommendations or advisories regarding actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lod
    -0.17
    cke
    -0.17
    ucc
    -0.16
    eya
    -0.15
    adel
    -0.14
    ãģĬãĤĬ
    -0.14
    oyal
    -0.14
    fsp
    -0.14
    views
    -0.14
    اÙģت
    -0.14
    POSITIVE LOGITS
    ered
    0.39
    nt
    0.37
    ering
    0.36
     be
    0.27
    NT
    0.24
    該
    0.23
    /c
    0.22
    ers
    0.18
    /w
    0.18
    ÂŃn
    0.17
    Act Density 0.078%

    No Known Activations