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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Based on"

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "Based on," indicating references to evidence or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shr
    -0.70
    istors
    -0.70
    ivering
    -0.67
    apo
    -0.67
    adra
    -0.67
    dimension
    -0.66
    icut
    -0.65
    imm
    -0.65
    arthy
    -0.65
    avez
    -0.64
    POSITIVE LOGITS
    tesy
    0.78
     loosely
    0.77
    ¥
    0.75
    ccording
    0.72
    awaru
    0.72
    Based
    0.67
    edience
    0.66
     citiz
    0.66
     veter
    0.66
    ¶æ
    0.65
    Act Density 0.014%

    No Known Activations