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

    Neuronpedia

    INDEX
    Explanations

    words related to advice or guidance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "ise" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.66
     srf
    -0.57
    halla
    -0.57
    sid
    -0.57
    ascal
    -0.57
    ¥ŀ
    -0.56
     Narr
    -0.56
    dies
    -0.54
    é¾
    -0.54
    src
    -0.54
    POSITIVE LOGITS
    ppe
    0.98
    ise
    0.91
    vich
    0.88
    veland
    0.87
    olate
    0.79
    iry
    0.76
    ises
    0.76
    ction
    0.75
    ases
    0.75
    vic
    0.73
    Act Density 0.016%

    No Known Activations