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

    Neuronpedia

    INDEX
    Explanations

    specific words related to the action of adjusting controls or parameters

    oai_token-act-pair · gpt-3.5-turbo

    references to dialing or connection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    videos
    -0.71
     EntityItem
    -0.69
    ãĤº
    -0.67
    BAT
    -0.66
    è¦ļéĨĴ
    -0.66
    âĺħâĺħ
    -0.64
    DF
    -0.63
     ABE
    -0.62
    LOD
    -0.62
    RI
    -0.61
    POSITIVE LOGITS
    ysis
    1.60
    tone
    1.00
    ect
    0.91
     dial
    0.88
    dial
    0.83
    ength
    0.82
    ogue
    0.80
    tops
    0.80
    polit
    0.79
    ogs
    0.78
    Act Density 0.017%

    No Known Activations