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

    Neuronpedia

    INDEX
    Explanations

    words related to patching and fixing issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "pat"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Afric
    -0.81
    ADE
    -0.72
    vous
    -0.70
     Abyssal
    -0.69
    ãħĭ
    -0.67
    STD
    -0.63
     casting
    -0.62
    shapeshifter
    -0.62
    ð
    -0.62
    DIV
    -0.62
    POSITIVE LOGITS
    ients
    1.46
    riots
    1.39
    terson
    1.29
    ricia
    1.26
    riot
    1.24
    roleum
    1.11
    rol
    1.06
    ricks
    1.05
    igious
    0.97
    ient
    0.96
    Act Density 0.009%

    No Known Activations