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

    Neuronpedia

    INDEX
    Explanations

    segments introducing conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Francesco
    -0.17
     italian
    -0.16
    æ½®
    -0.15
    ellar
    -0.15
     Hungarian
    -0.15
     discrepan
    -0.15
     Romanian
    -0.15
    ogh
    -0.14
    826
    -0.14
    onym
    -0.14
    POSITIVE LOGITS
     Bolivia
    0.52
     Bol
    0.45
     Morales
    0.44
     bol
    0.36
     Ðijол
    0.34
     Evo
    0.34
    bol
    0.33
     Bolton
    0.31
    Mor
    0.26
     Bolt
    0.26
    Act Density 0.000%

    No Known Activations