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

    Neuronpedia

    INDEX
    Explanations

    mentions of detectives and police officers in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    the word "Detective" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miscarriage
    -0.71
    xual
    -0.69
     sshd
    -0.69
    steen
    -0.67
    blind
    -0.62
    margin
    -0.61
     substitute
    -0.61
    volume
    -0.60
    giving
    -0.60
     heights
    -0.59
    POSITIVE LOGITS
    ective
    1.54
    ection
    1.52
    ected
    1.41
    ector
    1.29
    ailed
    1.24
    ect
    1.22
    ECT
    1.01
    ail
    1.00
    ECTION
    1.00
    achment
    0.99
    Act Density 0.025%

    No Known Activations