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

    Neuronpedia

    INDEX
    Explanations

    references to public relations (PR)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enheim
    -0.16
     McKay
    -0.15
    ild
    -0.15
    arend
    -0.15
    enberg
    -0.15
     enlarged
    -0.15
    o
    -0.14
     enlarg
    -0.14
    ourn
    -0.14
     impulse
    -0.14
    POSITIVE LOGITS
    flater
    0.15
    åĢ
    0.15
     kus
    0.15
    enty
    0.15
    £o
    0.15
    öm
    0.15
    uste
    0.14
    OptionPane
    0.14
    nde
    0.14
    Ю
    0.14
    Act Density 0.012%

    No Known Activations