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

    Neuronpedia

    INDEX
    Explanations

    occurrences of phrases that specify a relationship to an object or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    instein
    -0.16
    .Sdk
    -0.14
    _marks
    -0.14
    @Id
    -0.14
    .synthetic
    -0.14
    寺
    -0.14
     addCriterion
    -0.14
    addin
    -0.14
    ÏįÏĦε
    -0.13
    ázd
    -0.13
    POSITIVE LOGITS
    aho
    0.18
    pile
    0.17
    ahoo
    0.15
    aterno
    0.15
    sn
    0.15
    away
    0.14
    /sn
    0.14
    stan
    0.14
    bine
    0.14
    ump
    0.14
    Act Density 0.253%

    No Known Activations