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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong opinions and personal preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliz
    -0.17
    esin
    -0.16
    ç¬
    -0.15
    ìľ¼ëĭĪ
    -0.15
    raya
    -0.15
    ebi
    -0.14
    criptor
    -0.14
    ossa
    -0.13
    afone
    -0.13
    sume
    -0.13
    POSITIVE LOGITS
    memberOf
    0.14
     entr
    0.14
    argv
    0.14
    -gap
    0.13
    oro
    0.13
     Punch
    0.13
    664
    0.13
    .Commit
    0.13
     Bias
    0.13
    berg
    0.13
    Act Density 0.063%

    No Known Activations