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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial figures or amounts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that represent monetary values or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uma
    -0.69
    NAS
    -0.67
    Rot
    -0.64
    MSN
    -0.63
     Refresh
    -0.63
    CT
    -0.61
    ================
    -0.60
    RAW
    -0.60
    atures
    -0.59
     Fall
    -0.58
    POSITIVE LOGITS
    lihood
    0.89
     hypot
    0.63
     imitation
    0.62
     adaptations
    0.60
     gag
    0.60
     sarcastic
    0.59
    going
    0.59
     CoC
    0.58
     insulting
    0.57
     expel
    0.57
    Act Density 0.224%

    No Known Activations