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

    Neuronpedia

    INDEX
    Explanations

    the word "additional" indicating supplementary information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MERCHANTABILITY
    -0.16
    banks
    -0.15
    ÑĢай
    -0.15
    tram
    -0.14
    oron
    -0.14
     MethodInfo
    -0.14
    ÄĽla
    -0.14
    lero
    -0.13
    oshi
    -0.13
    Exited
    -0.13
    POSITIVE LOGITS
    endum
    0.19
    ams
    0.17
    resse
    0.15
    dued
    0.15
    pls
    0.15
    eum
    0.15
    alte
    0.15
     Eins
    0.14
    ately
    0.14
    ipes
    0.13
    Act Density 0.013%

    No Known Activations