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

    Neuronpedia

    INDEX
    Explanations

    verbs related to speculation or theorizing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theoretical concepts and conjectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unequ
    -0.86
    ophon
    -0.76
     actionGroup
    -0.72
    VERTISEMENT
    -0.70
    catentry
    -0.62
    ophone
    -0.61
     stamps
    -0.61
    SUP
    -0.60
    DOC
    -0.59
     voic
    -0.57
    POSITIVE LOGITS
    fy
    0.81
    atively
    0.80
    aneously
    0.73
    umar
    0.73
    ishly
    0.73
    peak
    0.71
    ially
    0.70
    essler
    0.68
    poke
    0.68
    edly
    0.67
    Act Density 0.111%

    No Known Activations