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

    Neuronpedia

    INDEX
    Explanations

    verbs related to communication and expression

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and communication issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.79
     assorted
    -0.61
    yssey
    -0.58
     Millennium
    -0.57
     Cotton
    -0.56
    appa
    -0.56
    rather
    -0.56
    itton
    -0.54
    ggles
    -0.54
    ugi
    -0.54
    POSITIVE LOGITS
     anymore
    1.91
     nor
    1.57
     necessarily
    1.36
     adequately
    1.20
     anywhere
    1.19
     lightly
    1.19
     consciously
    1.15
     enough
    1.14
     properly
    1.14
     whatsoever
    1.11
    Act Density 0.370%

    No Known Activations