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

    Neuronpedia

    INDEX
    Explanations

    actionable phrases indicating personal commitment or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isque
    -0.18
    uess
    -0.16
    ä»Ģä¹Ī
    -0.14
     Farr
    -0.14
    ikes
    -0.13
    ä»Ģ
    -0.13
    orz
    -0.13
    noinspection
    -0.13
    .Metadata
    -0.13
    ä¸Ģç§į
    -0.13
    POSITIVE LOGITS
     nobody
    0.17
    soever
    0.16
     ple
    0.16
    Æ°
    0.15
     needed
    0.15
    oola
    0.15
    opsy
    0.15
    itzer
    0.15
    rech
    0.15
    ystal
    0.14
    Act Density 0.040%

    No Known Activations