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

    Neuronpedia

    INDEX
    Explanations

    statements that emphasize truth or authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apatalk
    -0.59
    vstack
    -0.53
    addington
    -0.53
    esity
    -0.48
     hornet
    -0.47
    nibus
    -0.47
    ubarak
    -0.47
    tisation
    -0.46
    aronder
    -0.46
    apad
    -0.46
    POSITIVE LOGITS
     true
    1.37
     True
    1.27
    True
    1.25
    true
    1.25
     TRUE
    1.23
    TRUE
    1.14
     verdadero
    1.00
     truest
    0.98
     truth
    0.92
     Verdad
    0.92
    Act Density 0.162%

    No Known Activations