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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to proximity and near events or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CODE
    -0.68
     behav
    -0.65
     Doodle
    -0.63
     Mahjong
    -0.61
     assurances
    -0.60
     Dillon
    -0.58
     Zy
    -0.58
     msec
    -0.58
    KC
    -0.57
     respectively
    -0.57
    POSITIVE LOGITS
    obl
    0.77
    thur
    0.74
    clock
    0.73
    aucas
    0.73
    itals
    0.73
    iHUD
    0.71
    ctic
    0.69
    Interstitial
    0.69
    ulkan
    0.68
     end
    0.68
    Act Density 0.106%

    No Known Activations