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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pretend" followed by an action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pretend" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĨij
    -0.71
    OTOS
    -0.67
    vez
    -0.67
    ccording
    -0.64
    Bio
    -0.63
    States
    -0.61
    interrupted
    -0.60
    APH
    -0.59
    Ger
    -0.58
    ilings
    -0.58
    POSITIVE LOGITS
     pretend
    0.82
    querade
    0.81
    arial
    0.81
     pas
    0.80
    entious
    0.76
     pretending
    0.75
    ãĥ¼ãĥĨãĤ£
    0.75
    cha
    0.74
     pretended
    0.74
     forgot
    0.71
    Act Density 0.010%

    No Known Activations