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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases consisting of two parts

    oai_token-act-pair · gpt-3.5-turbo

    playful or whimsical expressions and non-standard language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.81
    ãĥ¯ãĥ³
    -0.73
    STD
    -0.69
    çĶ°
    -0.66
     Fukushima
    -0.65
    ulner
    -0.65
     Monetary
    -0.64
    Services
    -0.64
    TEXTURE
    -0.63
    DragonMagazine
    -0.63
    POSITIVE LOGITS
    bour
    0.75
     unic
    0.73
     gard
    0.66
     bour
    0.66
     dotted
    0.65
    ween
    0.64
    Ãł
    0.63
     drawer
    0.62
     cookie
    0.62
     crocod
    0.60
    Act Density 0.211%

    No Known Activations