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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mechanical or technical procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to communication and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    humans
    -0.55
     unborn
    -0.55
    ukong
    -0.54
     Tycoon
    -0.52
    soDeliveryDate
    -0.52
    ankind
    -0.52
    ":{"
    -0.51
    pire
    -0.51
    ASHINGTON
    -0.51
    ãģ®éŃĶ
    -0.50
    POSITIVE LOGITS
     understatement
    0.73
     translator
    0.63
     sarc
    0.60
     typing
    0.60
     ital
    0.57
    dding
    0.57
    swer
    0.55
     commenting
    0.55
     typew
    0.54
     confidentiality
    0.53
    Act Density 1.631%

    No Known Activations