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

    Neuronpedia

    INDEX
    Explanations

    key elements related to identity and self-discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folios
    -0.15
     sketch
    -0.15
    jah
    -0.14
     carr
    -0.14
    Ðĭ
    -0.14
     note
    -0.14
    _udp
    -0.14
    .cx
    -0.13
    roj
    -0.13
    .Dependency
    -0.13
    POSITIVE LOGITS
     meanwhile
    0.16
     Meanwhile
    0.16
    .Comp
    0.15
     Bulk
    0.14
    orney
    0.14
     Roe
    0.14
    .Enums
    0.13
    arte
    0.13
    IVER
    0.13
     Dixon
    0.13
    Act Density 0.079%

    No Known Activations