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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software development and instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software updates and application development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.68
     thereafter
    -0.66
    abouts
    -0.65
    etheless
    -0.65
     denies
    -0.63
     helicop
    -0.63
     afterward
    -0.63
    Otherwise
    -0.63
    Cause
    -0.63
     belie
    -0.61
    POSITIVE LOGITS
    ktop
    0.90
    Congratulations
    0.85
     Congratulations
    0.83
     naughty
    0.72
     countdown
    0.71
    reetings
    0.71
    cle
    0.69
     FAT
    0.69
     PAX
    0.64
    bye
    0.64
    Act Density 0.571%

    No Known Activations