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

    Neuronpedia

    INDEX
    Explanations

    references to quantities or articles in a descriptive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MM
    -0.15
    cf
    -0.14
    ipel
    -0.14
    guard
    -0.14
    MAN
    -0.14
    agascar
    -0.13
    icion
    -0.13
    umat
    -0.13
    MB
    -0.13
    ubbo
    -0.13
    POSITIVE LOGITS
    iversal
    0.18
    maal
    0.18
    526
    0.17
    pha
    0.16
     altro
    0.15
    ltra
    0.14
     autre
    0.14
    огда
    0.14
    krom
    0.14
    ERGY
    0.14
    Act Density 0.033%

    No Known Activations