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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases indicating categories, qualities, or descriptions related to transformations and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osi
    -0.18
    croft
    -0.15
    imb
    -0.14
     pel
    -0.14
    era
    -0.14
    reads
    -0.14
     FORE
    -0.14
     advoc
    -0.13
     precisa
    -0.13
    unj
    -0.13
    POSITIVE LOGITS
    rego
    0.18
    uality
    0.16
    Argb
    0.15
    uke
    0.15
    .AllowUser
    0.14
    ÑĢоÑģ
    0.14
    uais
    0.14
    ennial
    0.14
    363
    0.14
    elder
    0.14
    Act Density 0.025%

    No Known Activations