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

    Neuronpedia

    INDEX
    Explanations

    words related to deception and misleading practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ήλ
    -0.15
    ammad
    -0.14
    tro
    -0.14
     Mobility
    -0.13
    eri
    -0.13
    aber
    -0.13
     InitializeComponent
    -0.13
     mob
    -0.13
    tura
    -0.13
    ween
    -0.13
    POSITIVE LOGITS
    Duplicates
    0.16
    кол
    0.15
    uters
    0.15
    ilst
    0.15
    noch
    0.15
    NSNotification
    0.15
    788
    0.14
    jde
    0.14
     Liberation
    0.14
    esis
    0.14
    Act Density 0.009%

    No Known Activations