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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software updates and patches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of unusual or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.73
     guiActiveUnfocused
    -0.69
     scatter
    -0.69
    anwhile
    -0.66
     detached
    -0.64
     minim
    -0.64
    odan
    -0.63
     rooting
    -0.63
     swept
    -0.63
     BMC
    -0.62
    POSITIVE LOGITS
    £
    1.14
    į
    1.02
    ı
    1.02
    ¹
    0.99
    º
    0.95
    Ĭ
    0.95
    âĢķ
    0.95
    âĸº
    0.95
    ¿
    0.93
    ¡
    0.92
    Act Density 0.553%

    No Known Activations