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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Fun"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Fun" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Centauri
    -0.72
     Ange
    -0.66
     Ãľ
    -0.64
     Amon
    -0.62
    Minimum
    -0.60
    xual
    -0.59
     Twain
    -0.59
     praises
    -0.58
     Canter
    -0.56
     peers
    -0.56
    POSITIVE LOGITS
    nel
    1.48
    eral
    1.46
    nels
    1.41
    imation
    1.38
    ctions
    1.29
    nell
    1.22
    ctors
    1.10
    geoning
    1.08
    ERAL
    1.07
    ctor
    1.07
    Act Density 0.029%

    No Known Activations