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

    Neuronpedia

    INDEX
    Explanations

    adjectives that indicate significance or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     دیکھیے
    -0.84
     AppModule
    -0.78
    })));
    -0.70
    ','#
    -0.68
    iffance
    -0.67
     تضيفلها
    -0.66
    ?,?,
    -0.65
    .~(\
    -0.65
    WriteLiteral
    -0.64
     Мексичка
    -0.64
    POSITIVE LOGITS
    Datuak
    0.74
    ftagPool
    0.58
    ctory
    0.55
     ones
    0.53
     and
    0.53
    ുള്ള
    0.51
     वाला
    0.49
    enschappelijke
    0.48
    うち
    0.47
     liberi
    0.47
    Act Density 0.307%

    No Known Activations