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

    Neuronpedia

    INDEX
    Explanations

    references to influences or sources within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignum
    -0.18
    nete
    -0.16
    .sourceforge
    -0.16
    ivec
    -0.15
    iliz
    -0.15
    ábado
    -0.15
    .UnitTesting
    -0.15
    _KP
    -0.15
    abet
    -0.14
    ARRANT
    -0.14
    POSITIVE LOGITS
    ats
    0.16
     t
    0.15
     Pul
    0.14
    ÑĤого
    0.14
    UGIN
    0.14
    337
    0.14
    QRS
    0.13
     solic
    0.13
    osa
    0.13
     Enc
    0.13
    Act Density 0.098%

    No Known Activations