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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the addition of new information or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
    etre
    -0.16
    ضا
    -0.16
    ken
    -0.15
    ÑĢаÑĤи
    -0.15
    .mc
    -0.15
    ib
    -0.15
    æĬ
    -0.15
    unu
    -0.14
     Jeho
    -0.14
    POSITIVE LOGITS
    ict
    0.15
    ToPoint
    0.14
    VL
    0.14
     note
    0.14
    eacher
    0.14
    esa
    0.14
    APER
    0.13
     fine
    0.13
    ALE
    0.13
    iction
    0.13
    Act Density 0.020%

    No Known Activations