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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.69
     الحره
    -0.67
    dova
    -0.49
    áda
    -0.48
    verdad
    -0.47
     Verdad
    -0.46
    waard
    -0.46
    bux
    -0.46
     departments
    -0.44
     собой
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
     BrowserModule
    0.68
     uska
    0.61
    PhysRevLett
    0.58
     ComVisible
    0.57
    UnusedPrivate
    0.53
     Савезне
    0.53
    IVEREF
    0.52
     Barbarian
    0.51
    afficheront
    0.51
    Act Density 0.514%

    No Known Activations