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

    Neuronpedia

    INDEX
    Explanations

    phrases related to underscoring importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating inevitability or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.77
    iphate
    -0.71
    cular
    -0.69
    oshenko
    -0.69
     pitted
    -0.65
    raltar
    -0.65
    aeda
    -0.65
     bombed
    -0.64
    uilt
    -0.64
    opted
    -0.64
    POSITIVE LOGITS
    Luck
    0.73
    hew
    0.66
     [|
    0.65
     Reader
    0.65
    math
    0.65
     Hun
    0.64
     HuffPost
    0.61
    fs
    0.61
     Survivor
    0.59
     Percy
    0.59
    Act Density 0.090%

    No Known Activations