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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or sentiments often related to dissatisfaction and disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.16
    @mail
    -0.16
    atre
    -0.16
    avel
    -0.15
    isi
    -0.15
    nar
    -0.15
    ame
    -0.14
    apid
    -0.14
    rts
    -0.14
    θη
    -0.14
    POSITIVE LOGITS
    823
    0.16
    uju
    0.15
     Eck
    0.15
    719
    0.14
    shit
    0.14
    ovny
    0.14
     Kak
    0.13
     Webb
    0.13
    ifacts
    0.13
    466
    0.13
    Act Density 0.056%

    No Known Activations