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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate opinions or assertions related to specifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foon
    -0.51
    ఓ
    -0.50
    }{*}{
    -0.49
     Pru
    -0.49
    myra
    -0.49
    alova
    -0.48
     abgerufen
    -0.48
    grana
    -0.47
     □
    -0.47
    teil
    -0.46
    POSITIVE LOGITS
     cioè
    0.93
    tså
    0.82
    ThroughAttribute
    0.79
    verwijspagina
    0.76
     TextInputType
    0.72
     يتيمه
    0.72
    즉
    0.71
    0.71
    invokeLater
    0.69
    EditorBrowsable
    0.68
    Act Density 0.265%

    No Known Activations