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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "once" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osis
    -0.81
    rals
    -0.76
    ocol
    -0.73
    usha
    -0.70
    LESS
    -0.70
    externalActionCode
    -0.69
    OG
    -0.69
    IELD
    -0.69
    needs
    -0.68
    EVA
    -0.68
    POSITIVE LOGITS
     Bucc
    0.77
     tasted
    0.73
     glimps
    0.72
     dreamed
    0.72
    handedly
    0.72
     belonged
    0.71
     married
    0.70
     again
    0.69
     harb
    0.69
     fallen
    0.68
    Act Density 0.026%

    No Known Activations