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

    Neuronpedia

    INDEX
    Explanations

    information or details that are exclusive or secret

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scoop" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.67
    TERN
    -0.65
    nces
    -0.63
    repeat
    -0.63
     juvenile
    -0.63
     livest
    -0.63
     Glob
    -0.62
    wealth
    -0.61
    lihood
    -0.61
    PRES
    -0.61
    POSITIVE LOGITS
     scoop
    1.26
    oops
    0.86
    hest
    0.85
    atform
    0.83
    veland
    0.83
    ilus
    0.81
    irtual
    0.80
    iest
    0.80
    feed
    0.79
    iness
    0.77
    Act Density 0.004%

    No Known Activations