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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and lists

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings or order in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.81
     authority
    -0.76
     tremend
    -0.74
     behav
    -0.73
     inward
    -0.67
    uggest
    -0.67
    izons
    -0.65
     moder
    -0.65
     rule
    -0.65
     heroine
    -0.64
    POSITIVE LOGITS
     Learns
    0.81
     Bye
    0.78
     Provided
    0.78
     TBD
    0.77
     Scores
    0.75
     Unknown
    0.71
    59
    0.71
    YES
    0.70
    57
    0.69
    adem
    0.69
    Act Density 0.117%

    No Known Activations