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

    Neuronpedia

    INDEX
    Explanations

    references to correspondence and reporting related to events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HeaderCode
    -0.16
    ãģĤãĤĬ
    -0.15
    _Tis
    -0.15
    annotate
    -0.15
    é¾Ħ
    -0.15
    racat
    -0.14
    аний
    -0.14
    ¼
    -0.14
    loud
    -0.14
    izard
    -0.14
    POSITIVE LOGITS
    ent
    0.72
    ents
    0.63
    ence
    0.55
    ENT
    0.51
    ency
    0.50
    ently
    0.47
    ente
    0.43
    ences
    0.43
    encies
    0.42
    ENTS
    0.41
    Act Density 0.046%

    No Known Activations