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

    Neuronpedia

    INDEX
    Explanations

    adjectives and participles that describe characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ust
    -0.15
    rike
    -0.15
    zioni
    -0.14
    rij
    -0.14
    alytics
    -0.14
    iginal
    -0.14
    *)_
    -0.14
    å«
    -0.13
     Strikes
    -0.13
     eof
    -0.13
    POSITIVE LOGITS
    upo
    0.17
    etically
    0.16
    ly
    0.15
    ?
    0.15
    ically
    0.15
    istically
    0.14
    uably
    0.14
    emente
    0.14
    izing
    0.14
    ELY
    0.14
    Act Density 0.247%

    No Known Activations