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

    Neuronpedia

    INDEX
    Explanations

    mentions of kidnappings or related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to kidnapping and kidnappers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.82
    gard
    -0.80
    Cola
    -0.72
    iquette
    -0.71
    cyclop
    -0.65
    acea
    -0.63
     Dynamics
    -0.62
     denomin
    -0.61
    ube
    -0.59
     Glob
    -0.59
    POSITIVE LOGITS
     kidnapped
    1.03
     abducted
    0.99
     kidnap
    0.95
     kidnapping
    0.93
     abduct
    0.90
     abduction
    0.86
    appings
    0.82
     kidn
    0.78
     ransom
    0.75
     hostage
    0.74
    Act Density 0.017%

    No Known Activations