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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rig
    -0.16
    834
    -0.16
     Kov
    -0.15
    ND
    -0.14
    ess
    -0.14
    NDER
    -0.14
    isk
    -0.13
    itol
    -0.13
     Keller
    -0.13
    exus
    -0.13
    POSITIVE LOGITS
     Wayback
    0.16
    alous
    0.15
    ÑĹ
    0.14
    iry
    0.14
    dition
    0.14
    enames
    0.14
     걸
    0.14
    VRT
    0.14
    ibrary
    0.13
    ves
    0.13
    Act Density 0.009%

    No Known Activations