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

    Neuronpedia

    INDEX
    Explanations

    references to criminal activity and cyber threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resc
    -0.15
    aves
    -0.15
    ritch
    -0.14
    \Module
    -0.14
    ione
    -0.14
    Escort
    -0.13
    escort
    -0.13
    aghan
    -0.13
     participating
    -0.13
     aver
    -0.13
    POSITIVE LOGITS
     targeting
    0.32
     target
    0.30
    target
    0.26
    Target
    0.23
     targets
    0.23
     intent
    0.23
     Target
    0.22
    Targets
    0.21
    arget
    0.21
    ,target
    0.21
    Act Density 0.269%

    No Known Activations