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

    Neuronpedia

    INDEX
    Explanations

    verbs and sentences where someone expresses an opinion or communicates information

    oai_token-act-pair · gpt-3.5-turbo

    statements made by individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.72
    acial
    -0.72
    bows
    -0.70
    chnology
    -0.67
    iber
    -0.66
    acters
    -0.66
    ember
    -0.65
    20439
    -0.65
    endered
    -0.64
    holm
    -0.63
    POSITIVE LOGITS
     Forbes
    0.71
     Luck
    0.70
     Rodgers
    0.67
     Crosby
    0.67
     Vernon
    0.65
     Gallup
    0.65
     plaus
    0.63
     detractors
    0.62
     economist
    0.62
    said
    0.62
    Act Density 0.521%

    No Known Activations