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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "As always" followed by a statement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating repetition or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dri
    -0.73
    wr
    -0.69
    relations
    -0.66
    throw
    -0.61
    orate
    -0.61
     dyn
    -0.60
    relative
    -0.60
    amins
    -0.60
     Wr
    -0.60
     vomit
    -0.60
    POSITIVE LOGITS
     redes
    0.78
    ubi
    0.74
     proceeds
    0.68
     disclaim
    0.68
     patiently
    0.67
     approached
    0.65
    ________________________________________________________________
    0.64
     clarified
    0.63
    iability
    0.63
     corrected
    0.63
    Act Density 0.046%

    No Known Activations