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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive and negative assessments or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive or favorable conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.61
    tein
    -0.56
     Prosecut
    -0.56
     Iraq
    -0.53
    mbudsman
    -0.52
    ghazi
    -0.52
    exit
    -0.49
     discriminatory
    -0.49
     Communists
    -0.49
     militias
    -0.49
    POSITIVE LOGITS
     newcom
    0.60
    nown
    0.60
     Neon
    0.56
    rawdownloadcloneembedreportprint
    0.55
     sci
    0.54
     rave
    0.54
     genre
    0.52
     Uncharted
    0.52
    canon
    0.51
     anime
    0.51
    Act Density 2.294%

    No Known Activations