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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific prepositions and articles in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilitation
    -0.16
    croll
    -0.15
     Bam
    -0.14
    terr
    -0.14
    erie
    -0.14
    SEX
    -0.14
    'gc
    -0.14
    ignum
    -0.13
    Č
    -0.13
    stellung
    -0.13
    POSITIVE LOGITS
     same
    0.17
    μοί
    0.15
    ottle
    0.15
     meantime
    0.14
    449
    0.14
    amura
    0.14
     following
    0.14
     wake
    0.14
    same
    0.14
    abile
    0.14
    Act Density 0.013%

    No Known Activations