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

    Neuronpedia

    INDEX
    Explanations

    instances of citations or references

    oai_token-act-pair · gpt-3.5-turbo

    closed brackets and list-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unwanted
    -0.65
    oes
    -0.65
    oe
    -0.63
    vier
    -0.63
    onite
    -0.61
    Ń·
    -0.61
    ¿
    -0.59
     SERV
    -0.58
    ciating
    -0.57
     fatig
    -0.57
    POSITIVE LOGITS
     ,
    0.73
    eous
    0.72
    TPS
    0.72
    âĨ
    0.72
    REDACTED
    0.71
     onwards
    0.70
    kson
    0.67
    externalActionCode
    0.67
    figure
    0.65
    mph
    0.65
    Act Density 0.049%

    No Known Activations