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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strength or robustness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buz
    -0.16
    zem
    -0.15
    zend
    -0.15
    ushi
    -0.15
    ogg
    -0.15
    rganization
    -0.15
    STANCE
    -0.15
    ikan
    -0.14
     åĸ
    -0.14
    upert
    -0.14
    POSITIVE LOGITS
    holds
    0.17
    _weak
    0.16
     Strong
    0.16
    /we
    0.15
    assen
    0.15
    ,strong
    0.15
    ASSES
    0.15
     strong
    0.15
     hitters
    0.15
    -strong
    0.14
    Act Density 0.018%

    No Known Activations