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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suspicion or being suspected of a crime

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion or being suspected of a crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uits
    -0.73
    ansk
    -0.73
    hire
    -0.72
    skill
    -0.72
    ithering
    -0.71
    anche
    -0.71
    ourses
    -0.70
    options
    -0.70
    uden
    -0.69
    hare
    -0.68
    POSITIVE LOGITS
    lessly
    0.96
     suspicious
    0.77
     culprit
    0.77
     wrongdoing
    0.76
    worthiness
    0.76
     suspicions
    0.75
     motives
    0.74
     arson
    0.73
     suspicion
    0.73
     suspect
    0.72
    Act Density 0.051%

    No Known Activations