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

    Neuronpedia

    INDEX
    Explanations

    punctuation related to lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and special characters, particularly parenthesis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hust
    -0.74
     assum
    -0.73
     imagining
    -0.69
     intu
    -0.67
     themselves
    -0.66
     champion
    -0.66
     skirts
    -0.65
     fleeing
    -0.65
     demographic
    -0.65
     patri
    -0.63
    POSITIVE LOGITS
    Reviewer
    1.03
     Duration
    0.80
     Continued
    0.78
     CONTIN
    0.74
     Donation
    0.73
     Comes
    0.73
     Take
    0.73
    rition
    0.72
    RAW
    0.71
     Stick
    0.71
    Act Density 1.026%

    No Known Activations