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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating the topic or focus of a discussion or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a progression or continuation of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullah
    -0.84
    icio
    -0.72
     Horus
    -0.72
    ament
    -0.70
    ablo
    -0.66
    idable
    -0.62
    ature
    -0.62
    ificent
    -0.61
    ipation
    -0.59
    uminati
    -0.59
    POSITIVE LOGITS
    lems
    1.01
    verning
    0.98
    vt
    0.93
    ggle
    0.91
    Ń·
    0.91
     overboard
    0.91
    eker
    0.85
     unnoticed
    0.80
     viral
    0.80
    ©¶æ
    0.79
    Act Density 0.097%

    No Known Activations