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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions associated with interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢеж
    -0.15
     standing
    -0.15
     seq
    -0.14
     infinite
    -0.14
     rounding
    -0.14
    BED
    -0.14
     wre
    -0.14
     Dumpster
    -0.14
     herk
    -0.13
     Wire
    -0.13
    POSITIVE LOGITS
    zar
    0.18
    autoload
    0.16
    zm
    0.15
    ÑĤаж
    0.15
    zv
    0.15
    .viewDidLoad
    0.14
    ZH
    0.14
    ews
    0.14
    092
    0.14
    791
    0.14
    Act Density 0.664%

    No Known Activations