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

    Neuronpedia

    INDEX
    Explanations

    technical phrases related to different methods or approaches

    oai_token-act-pair · gpt-3.5-turbo

    references to various techniques and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riel
    -0.72
    endar
    -0.72
    onen
    -0.71
    watching
    -0.66
    engers
    -0.63
     gloom
    -0.63
    joy
    -0.62
     Gallagher
    -0.62
    gur
    -0.61
    à
    -0.60
    POSITIVE LOGITS
    ologies
    1.23
     techniques
    0.95
     pioneered
    0.85
     employed
    0.83
     utilized
    0.82
    kit
    0.81
    ologically
    0.81
    OLOGY
    0.80
    ologic
    0.80
     technique
    0.76
    Act Density 0.052%

    No Known Activations