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

    Neuronpedia

    INDEX
    Explanations

    names or terms that contain "O" with special characters surrounding them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific special character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.96
    itably
    -0.72
    lda
    -0.68
    ioned
    -0.67
     scattering
    -0.65
    ctors
    -0.65
     Libyan
    -0.64
     scatter
    -0.63
     shack
    -0.62
     nucleus
    -0.61
    POSITIVE LOGITS
    ¹
    1.16
    º
    1.07
    £
    1.05
    ¬
    1.03
    į
    1.02
    ¡
    1.01
    ı
    1.01
    §
    1.00
    °
    0.98
    ħ
    0.97
    Act Density 0.375%

    No Known Activations