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

    Neuronpedia

    INDEX
    Explanations

    terms related to violent actions and legal implications surrounding assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entr
    -0.15
    stral
    -0.14
     generation
    -0.14
    ostat
    -0.14
    argout
    -0.14
     Cov
    -0.14
    paring
    -0.13
     Han
    -0.13
    //{{
    -0.13
    -found
    -0.13
    POSITIVE LOGITS
    amerate
    0.18
    able
    0.18
    ive
    0.17
    iveness
    0.17
    ively
    0.16
     tcb
    0.15
    aland
    0.15
    ors
    0.15
    343
    0.15
    rchive
    0.15
    Act Density 0.009%

    No Known Activations