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

    Neuronpedia

    INDEX
    Explanations

    instances of dishonesty and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sar
    -0.16
    illet
    -0.16
    оÑĢов
    -0.15
    lify
    -0.15
    tron
    -0.15
    chner
    -0.15
    .scalablytyped
    -0.15
    ILON
    -0.14
    408
    -0.14
    grily
    -0.14
    POSITIVE LOGITS
     told
    0.24
     about
    0.20
    uten
    0.16
    _about
    0.16
    -flat
    0.16
     sacks
    0.16
     detector
    0.16
    -about
    0.16
    berman
    0.15
    utenant
    0.15
    Act Density 0.024%

    No Known Activations