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

    Neuronpedia

    INDEX
    Explanations

    phrases related to misinformation or deception

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "misleading" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mun
    -0.71
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.68
    riot
    -0.67
    itar
    -0.66
    aldo
    -0.65
    ucha
    -0.63
    area
    -0.62
    mega
    -0.62
    ube
    -0.59
    cakes
    -0.59
    POSITIVE LOGITS
    ingly
    1.01
     misleading
    0.83
     misled
    0.80
    sters
    0.79
     deceive
    0.78
     mislead
    0.78
    fully
    0.75
    ulence
    0.71
     Disclosure
    0.69
    ulent
    0.69
    Act Density 0.026%

    No Known Activations