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

    Neuronpedia

    INDEX
    Explanations

    events or actions happening immediately or right after something else

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "immediately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.76
    midt
    -0.64
     ANGEL
    -0.64
    doctor
    -0.64
    pel
    -0.63
     Belt
    -0.63
    smanship
    -0.61
     Vend
    -0.60
    may
    -0.60
     Samurai
    -0.59
    POSITIVE LOGITS
    aneously
    1.12
     thereafter
    0.99
     identifiable
    0.91
    onding
    0.88
     recognizable
    0.87
     afterward
    0.82
     preceded
    0.79
     afterwards
    0.78
     gratification
    0.76
     Leilan
    0.75
    Act Density 0.023%

    No Known Activations