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

    Neuronpedia

    INDEX
    Explanations

    words related to tampering or proofing against tampering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tampering or alteration, particularly in the context of substances or evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.80
    doms
    -0.76
    sson
    -0.74
    stood
    -0.72
    sam
    -0.71
     XVI
    -0.68
     Borders
    -0.68
     Spectrum
    -0.68
     Directions
    -0.66
    osate
    -0.65
    POSITIVE LOGITS
     tam
    1.16
    pered
    0.98
     tampering
    0.94
    orah
    0.87
    pering
    0.83
    etry
    0.79
    itious
    0.78
    ritten
    0.78
    Toy
    0.74
    rodu
    0.70
    Act Density 0.015%

    No Known Activations