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

    Neuronpedia

    INDEX
    Explanations

    phrases related to documentation or references in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousel
    -0.16
    ismatch
    -0.15
    opoulos
    -0.15
    ksen
    -0.15
     adj
    -0.14
    outil
    -0.14
    otes
    -0.14
    okud
    -0.13
    eprom
    -0.13
    ogle
    -0.13
    POSITIVE LOGITS
     lame
    0.20
     ali
    0.17
     finest
    0.17
     scans
    0.17
     fend
    0.16
     corn
    0.16
     zam
    0.16
    ghi
    0.16
     bust
    0.15
     traverse
    0.15
    Act Density 0.002%

    No Known Activations