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

    Neuronpedia

    INDEX
    Explanations

    button classes indicating primary and warning statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DNEY
    -0.58
    Handlung
    -0.54
    PhysRev
    -0.52
     Wide
    -0.51
     fine
    -0.51
     ידי
    -0.51
     Bell
    -0.51
    Académie
    -0.51
     Mai
    -0.49
    阜
    -0.49
    POSITIVE LOGITS
    primary
    1.26
     primary
    1.01
    Primary
    0.95
     primaire
    0.89
     Primary
    0.87
     PRIMARY
    0.85
    danger
    0.83
    BagConstraints
    0.81
     primario
    0.77
     primaries
    0.76
    Act Density 0.040%

    No Known Activations