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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating an increase or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osemite
    -0.14
    hound
    -0.14
    Spot
    -0.14
    /Area
    -0.13
    uality
    -0.13
    von
    -0.13
    оÑģÑĢед
    -0.13
    ãģĹãģ®
    -0.13
    ecies
    -0.13
    671
    -0.13
    POSITIVE LOGITS
    endum
    0.31
    resse
    0.25
    -ons
    0.19
    uctor
    0.19
    /sub
    0.17
    tion
    0.17
    /remove
    0.17
    icted
    0.17
    ams
    0.17
    /rem
    0.17
    Act Density 0.074%

    No Known Activations