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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical data and quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or group experiences and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    binding
    -0.73
     whispering
    -0.71
     Kenobi
    -0.70
     objectionable
    -0.69
    tones
    -0.67
     voicing
    -0.67
     subversive
    -0.67
     Cannes
    -0.67
     BDS
    -0.65
     Aly
    -0.65
    POSITIVE LOGITS
     averaged
    1.47
     estimate
    1.23
     subtract
    1.19
     calculate
    1.15
     averages
    1.13
     tripled
    1.13
     racked
    1.10
     deducted
    1.07
     accounted
    1.07
     totaled
    1.07
    Act Density 0.370%

    No Known Activations