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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approximation or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.54
    :
    -0.53
     D
    -0.53
    ;
    -0.50
    ↵
    -0.50
    g
    -0.49
     Des
    -0.49
     Tag
    -0.49
     回
    -0.49
    5
    -0.48
    POSITIVE LOGITS
     Virtually
    1.22
    ctically
    1.20
     virtually
    1.20
     Practically
    1.15
     practically
    1.15
    verständlich
    1.09
    ^(@)
    1.08
    клопе
    1.07
     almost
    1.06
     nearly
    1.06
    Act Density 0.025%

    No Known Activations