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

    Neuronpedia

    INDEX
    Explanations

    instances where an action or event is repeated multiple times

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of frequency-related phrases and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORMATION
    -0.72
    Marginal
    -0.72
     Clothing
    -0.66
     Library
    -0.65
     Hide
    -0.64
    CVE
    -0.63
    arantine
    -0.62
    BIL
    -0.61
     Publication
    -0.61
    aria
    -0.60
    POSITIVE LOGITS
     sidx
    0.92
     consecut
    0.92
    enos
    0.74
    secut
    0.71
    aucas
    0.70
    numbered
    0.69
    iak
    0.67
    umatic
    0.67
    hur
    0.67
    uder
    0.66
    Act Density 0.180%

    No Known Activations