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

    Neuronpedia

    INDEX
    Explanations

    the name "Ras" occurring in texts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or titles, likely of people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.68
    anooga
    -0.67
     Lima
    -0.65
    alities
    -0.65
    asia
    -0.64
     Corpus
    -0.63
    ovies
    -0.63
    ertain
    -0.61
    ©
    -0.60
    ambers
    -0.59
    POSITIVE LOGITS
    senal
    1.39
    cliffe
    0.89
    uling
    0.81
    fect
    0.80
    haps
    0.79
    pees
    0.78
     Twice
    0.76
    utherford
    0.75
    Studio
    0.75
    spective
    0.74
    Act Density 0.223%

    No Known Activations