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

    Neuronpedia

    INDEX
    Explanations

    words expressing personal opinions or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of speech or quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Role
    -0.74
    taboola
    -0.69
    mol
    -0.66
    Charge
    -0.66
    oil
    -0.66
    eneg
    -0.65
     graded
    -0.64
    shut
    -0.63
    isol
    -0.62
    otin
    -0.61
    POSITIVE LOGITS
    orically
    0.73
     sarcast
    0.69
     Donna
    0.68
     Joyce
    0.68
     Dave
    0.68
     anecd
    0.67
    heny
    0.67
     Stef
    0.66
     bluntly
    0.66
     Angela
    0.66
    Act Density 0.056%

    No Known Activations