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

    Neuronpedia

    INDEX
    Explanations

    web addresses or references to official organizations and data resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     f
    -0.06
     (
    -0.06
     &
    -0.06
     buck
    -0.06
     Bob
    -0.05
    -0.05
     miss
    -0.05
     Arist
    -0.05
     br
    -0.05
     sa
    -0.05
    POSITIVE LOGITS
    Äįin
    0.08
    ONGL
    0.08
    ÄĽÅĻ
    0.07
    ariat
    0.07
    eron
    0.07
    éĻµ
    0.07
    ropa
    0.07
    icot
    0.07
     Abed
    0.07
    egov
    0.07
    Act Density 0.005%

    No Known Activations