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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suspicion and police activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    skill
    -0.74
    anche
    -0.72
    hare
    -0.72
    ourses
    -0.70
    jri
    -0.68
    psey
    -0.68
    sburg
    -0.68
    learning
    -0.68
    church
    -0.67
    wake
    -0.67
    POSITIVE LOGITS
    lessly
    0.85
     suspicious
    0.81
     suspects
    0.76
     suspect
    0.76
     motives
    0.69
     arson
    0.68
     suspicion
    0.67
     Activity
    0.67
    ostic
    0.66
    worthiness
    0.66
    Act Density 0.039%

    No Known Activations