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

    Neuronpedia

    INDEX
    Explanations

    words related to research, medical conditions, and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instead
    -0.72
    ?).
    -0.66
    instead
    -0.65
     Instead
    -0.64
    Instead
    -0.63
    就可以了
    -0.62
    就好了
    -0.61
     usw
    -0.60
    GEBURTSDATUM
    -0.59
    就行了
    -0.59
    POSITIVE LOGITS
     both
    1.42
     especially
    1.36
    especially
    1.34
    both
    1.30
    particularly
    1.30
    Especially
    1.26
     particularly
    1.25
     sowohl
    1.21
     zarówno
    1.20
     Especially
    1.19
    Act Density 0.598%

    No Known Activations