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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to danger and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ober
    -0.20
    IBC
    -0.15
    omba
    -0.15
    лиÑĤ
    -0.15
    hi
    -0.14
    cano
    -0.14
    uther
    -0.14
    mpi
    -0.14
    Äįe
    -0.14
    oth
    -0.14
    POSITIVE LOGITS
    iveau
    0.15
    ous
    0.14
    xmm
    0.14
    strup
    0.14
    _UID
    0.14
    imson
    0.14
    igar
    0.14
    -offset
    0.13
    resse
    0.13
    bor
    0.13
    Act Density 0.158%

    No Known Activations