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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to functions and variables

    oai_token-act-pair · gpt-3.5-turbo

    mathematical functions and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     migr
    -0.86
     sponsorship
    -0.80
     reception
    -0.78
     secretive
    -0.78
     congreg
    -0.77
     speeches
    -0.75
     approving
    -0.74
     informal
    -0.73
     catering
    -0.73
     conven
    -0.73
    POSITIVE LOGITS
    {\
    1.74
    {{
    1.52
    0
    1.52
    x
    1.43
    2
    1.41
    10000
    1.41
    1
    1.38
    ((
    1.38
    lambda
    1.37
    Math
    1.37
    Act Density 0.060%

    No Known Activations