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

    Neuronpedia

    INDEX
    Explanations

    Information related to legal or criminal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of relationships or relational dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.86
    plan
    -0.73
     Takeru
    -0.72
     buckle
    -0.63
    lda
    -0.63
     Rowling
    -0.63
     Tome
    -0.62
     Sung
    -0.61
    plin
    -0.61
     Lank
    -0.61
    POSITIVE LOGITS
    igion
    1.24
    iever
    1.02
    inqu
    1.02
    ief
    1.00
    iance
    0.99
    ights
    0.96
    iability
    0.95
    ieved
    0.92
    ighters
    0.88
    iable
    0.87
    Act Density 0.010%

    No Known Activations