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

    Neuronpedia

    INDEX
    Explanations

    phrases related to past behavior or performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a history or track record of actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ando
    -0.75
    agers
    -0.72
    hap
    -0.70
    tein
    -0.69
    ulp
    -0.68
    Stars
    -0.68
    ateurs
    -0.67
    ishers
    -0.67
    ople
    -0.66
    elsen
    -0.66
    POSITIVE LOGITS
     documented
    0.79
     dealings
    0.77
    acqu
    0.74
     proven
    0.69
     revolving
    0.69
     histories
    0.68
     reliability
    0.67
     abuser
    0.67
     conflicts
    0.67
     penchant
    0.67
    Act Density 0.080%

    No Known Activations