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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recommendations or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucc
    -0.16
    cke
    -0.16
    adel
    -0.15
    lod
    -0.15
    illery
    -0.15
    ichel
    -0.14
    иÑĤÑĥ
    -0.14
    اÙģت
    -0.14
    essen
    -0.14
    adena
    -0.14
    POSITIVE LOGITS
    ered
    0.38
    nt
    0.38
    ering
    0.35
     be
    0.28
    NT
    0.24
    該
    0.23
    /c
    0.21
     not
    0.20
    ers
    0.18
    n
    0.17
    Act Density 0.087%

    No Known Activations