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

    Neuronpedia

    INDEX
    Explanations

    words related to geological periods and events

    oai_token-act-pair · gpt-3.5-turbo

    specific keywords or phrases related to chat or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lets
    -0.81
    rencies
    -0.76
    Īè
    -0.69
    Balt
    -0.68
    banks
    -0.67
    oise
    -0.67
    alf
    -0.67
     interceptions
    -0.66
    let
    -0.66
    ½
    -0.66
    POSITIVE LOGITS
    REL
    0.74
    OGR
    0.73
    REM
    0.70
     attention
    0.69
    aneous
    0.66
    WC
    0.64
    omet
    0.61
     imperative
    0.61
    CW
    0.60
     cessation
    0.60
    Act Density 0.000%

    No Known Activations