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

    Neuronpedia

    INDEX
    Explanations

    links to external sources

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clin
    -0.79
     prey
    -0.76
     neb
    -0.71
     orche
    -0.70
     generation
    -0.69
     haunted
    -0.69
     coales
    -0.69
     mature
    -0.68
     transf
    -0.68
     hardened
    -0.67
    POSITIVE LOGITS
    PDF
    1.78
    emphasis
    1.67
    pdf
    1.66
    below
    1.54
    pictured
    1.53
    via
    1.47
    above
    1.43
    see
    1.42
    again
    1.39
    albeit
    1.37
    Act Density 0.089%

    No Known Activations