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

    Neuronpedia

    INDEX
    Explanations

    references to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iram
    -0.18
    iron
    -0.16
    åĪĩãĤĬ
    -0.15
    sig
    -0.15
    eder
    -0.15
    elling
    -0.15
    ires
    -0.15
    оÑģÑĤаÑĤ
    -0.15
    ooth
    -0.14
    ez
    -0.14
    POSITIVE LOGITS
    ence
    0.22
    ent
    0.21
    ently
    0.19
    leta
    0.19
    ENCE
    0.19
    aceous
    0.17
    ins
    0.17
     viol
    0.17
    -viol
    0.17
    ations
    0.16
    Act Density 0.005%

    No Known Activations