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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating presence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.77
    WebVitals
    -0.70
    ьажоргаш
    -0.68
    tonsoft
    -0.68
    UnsafeEnabled
    -0.68
    etheless
    -0.62
    audiovisuel
    -0.62
    ništvo
    -0.60
     oprot
    -0.60
    dafx
    -0.59
    POSITIVE LOGITS
    ®,
    0.58
    copyWith
    0.54
     LLC
    0.53
     aka
    0.53
    Autoritní
    0.53
    ™,
    0.51
    ⓘ
    0.50
    เภ
    0.49
    RegressionTest
    0.49
     dont
    0.49
    Act Density 1.284%

    No Known Activations