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

    Neuronpedia

    INDEX
    Explanations

    words related to the establishment or implementation of policies, rules, or procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "institute" and its variations or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EngineDebug
    -0.77
    WER
    -0.70
     thirds
    -0.63
    loaded
    -0.62
     Pipeline
    -0.61
    loading
    -0.61
    THER
    -0.61
    razil
    -0.60
     Navajo
    -0.60
    isexual
    -0.59
    POSITIVE LOGITS
     instit
    0.98
    itute
    0.88
     institute
    0.83
    itutional
    0.81
    utes
    0.80
    uates
    0.79
    rative
    0.79
    clair
    0.76
    uate
    0.76
    uated
    0.75
    Act Density 0.009%

    No Known Activations