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

    Neuronpedia

    INDEX
    Explanations

    phrases related to functionality and capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Consumes
    -0.53
    oje
    -0.49
    roek
    -0.49
    pendientes
    -0.46
     TextAlign
    -0.45
    rmızı
    -0.44
    itarian
    -0.44
    liegt
    -0.43
    epiece
    -0.43
    prehen
    -0.43
    POSITIVE LOGITS
     able
    2.78
     ability
    2.02
     Able
    1.75
    Able
    1.70
     Ability
    1.57
    able
    1.50
    Ability
    1.50
    能够
    1.41
     pouvoir
    1.41
    ability
    1.36
    Act Density 0.448%

    No Known Activations