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

    Neuronpedia

    INDEX
    Explanations

    phrases related to doubles or multiples of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to economic downturns or recessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uncond
    -0.70
     Mandal
    -0.56
    ################
    -0.56
     USL
    -0.56
     truly
    -0.56
    RAW
    -0.55
    uddin
    -0.55
     legion
    -0.54
    other
    -0.54
     Survivor
    -0.54
    POSITIVE LOGITS
    ammy
    1.09
    Russ
    0.74
    Unix
    0.73
    eds
    0.72
    rencies
    0.72
    Psy
    0.70
    isites
    0.69
    edly
    0.69
    alion
    0.68
    fect
    0.68
    Act Density 0.111%

    No Known Activations