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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.53
    __':
    -0.52
    Diwedd
    -0.50
    あえず
    -0.46
    esModule
    -0.46
    illion
    -0.45
    __':
    -0.45
    profess
    -0.42
     Heron
    -0.42
     Qua
    -0.41
    POSITIVE LOGITS
     Pourtant
    0.51
     mere
    0.45
     pourtant
    0.44
     slechts
    0.44
     endnu
    0.43
    仅仅
    0.41
     ändå
    0.40
     yet
    0.40
     enfans
    0.40
     ännu
    0.40
    Act Density 0.396%

    No Known Activations