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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.82
    )"),
    -0.74
    dafx
    -0.69
     _)
    -0.69
    "):
    -0.68
    )$}
    -0.67
    ")));
    -0.67
     autorytatywna
    -0.67
    licet
    -0.66
    unately
    -0.66
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.94
    ,
    0.63
    ;
    0.57
     înainte
    0.56
    ®,
    0.54
    .
    0.54
     nemico
    0.53
     negru
    0.53
     antichi
    0.52
    
    0.51
    Act Density 0.929%

    No Known Activations