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

    Neuronpedia

    INDEX
    Explanations

    listings and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okin
    -0.84
     cannibal
    -0.60
    interstitial
    -0.59
    anchester
    -0.58
    gha
    -0.58
     contag
    -0.57
    eson
    -0.57
     explan
    -0.57
    ornia
    -0.56
     isEnabled
    -0.56
    POSITIVE LOGITS
    /+
    1.07
    /-
    1.03
    -+-+-+-+
    0.97
    ï¸ı
    0.92
    -+
    0.82
    =~=~
    0.78
    -+-+
    0.74
    ×ķ
    0.73
    jp
    0.71
    γ
    0.70
    Act Density 0.098%

    No Known Activations