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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data and punctuation in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icit
    -0.16
    CSI
    -0.15
    xffffff
    -0.15
    ãģķãģ¾
    -0.14
    ÅĪ
    -0.14
    ABCDEFG
    -0.14
    IRA
    -0.14
    RITE
    -0.14
    ÑĢаж
    -0.13
    orro
    -0.13
    POSITIVE LOGITS
    andle
    0.19
     ET
    0.16
    jer
    0.16
     Analysis
    0.14
    uable
    0.14
    GPL
    0.14
     NOTES
    0.14
    622
    0.14
    andel
    0.14
     Recorded
    0.14
    Act Density 0.012%

    No Known Activations