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

    Neuronpedia

    INDEX
    Explanations

    instances of crime-related activities and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /spec
    -0.15
    chedulers
    -0.14
    former
    -0.14
    Photos
    -0.13
     Crusher
    -0.13
    -www
    -0.13
    612
    -0.13
     Powered
    -0.13
    oter
    -0.13
    eno
    -0.12
    POSITIVE LOGITS
     sen
    0.25
     sedan
    0.23
     han
    0.17
     str
    0.17
     Strait
    0.17
    Sent
    0.17
     sensation
    0.17
     Sed
    0.16
     efter
    0.16
    nici
    0.16
    Act Density 0.056%

    No Known Activations