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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'say' and related phrases indicating speech or expressions of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bih
    -0.16
    luv
    -0.15
    /out
    -0.15
    pot
    -0.14
    sta
    -0.13
    вала
    -0.13
    anova
    -0.13
    grund
    -0.13
    @qq
    -0.13
    igo
    -0.13
    POSITIVE LOGITS
    unct
    0.16
    urn
    0.15
     Chambers
    0.14
    çĢ¬
    0.14
    estre
    0.14
    /do
    0.14
    empre
    0.14
    /write
    0.14
    нез
    0.13
    /disc
    0.13
    Act Density 0.172%

    No Known Activations