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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating actions or getting started

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alie
    -0.15
    ened
    -0.15
    ols
    -0.14
    isi
    -0.14
    gars
    -0.14
     exc
    -0.14
    ůže
    -0.13
    spar
    -0.13
     spo
    -0.13
    brace
    -0.13
    POSITIVE LOGITS
    abase
    0.18
    icari
    0.17
     Jacobs
    0.17
    zÄħ
    0.17
    895
    0.17
     ìĭľìŀij
    0.16
    inem
    0.15
    601
    0.15
     Pey
    0.15
     Convers
    0.15
    Act Density 0.085%

    No Known Activations