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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" and analyze contexts where it indicates ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aar
    -0.17
     Lace
    -0.16
     Pie
    -0.15
    rij
    -0.15
     clap
    -0.14
    arken
    -0.14
    bcc
    -0.14
    ÏĢιÏĥ
    -0.13
    cent
    -0.13
     attr
    -0.13
    POSITIVE LOGITS
    AINS
    0.17
    aldi
    0.16
    á»ĩ
    0.15
    utan
    0.15
    ernels
    0.15
    CEL
    0.14
    igid
    0.14
    naments
    0.14
    æŁ±
    0.14
    enuity
    0.14
    Act Density 0.089%

    No Known Activations