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

    Neuronpedia

    INDEX
    Explanations

    actions related to organizing events or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to participation in events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     »
    -0.71
    .</
    -0.71
    Rat
    -0.65
    Image
    -0.63
    SPONSORED
    -0.61
    Anyway
    -0.61
     },
    -0.60
    ItemThumbnailImage
    -0.60
    IPS
    -0.60
    .*
    -0.59
    POSITIVE LOGITS
    stanbul
    0.64
     frust
    0.62
    enhagen
    0.62
    è¦ļéĨĴ
    0.62
     Mahjong
    0.61
    reditary
    0.60
    nsic
    0.60
    arij
    0.60
    anwhile
    0.58
    rontal
    0.57
    Act Density 0.459%

    No Known Activations