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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify support or assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errat
    -0.16
    StackNavigator
    -0.14
    931
    -0.14
    aint
    -0.14
    ackle
    -0.14
    izzo
    -0.14
     discussions
    -0.14
    RegularExpression
    -0.13
    ogg
    -0.13
    amment
    -0.13
    POSITIVE LOGITS
     ult
    0.28
     nod
    0.23
     heads
    0.23
     lesson
    0.22
     thumbs
    0.22
     gift
    0.22
     warning
    0.21
     taste
    0.21
     понÑıÑĤÑĮ
    0.20
     shove
    0.20
    Act Density 0.170%

    No Known Activations