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

    Neuronpedia

    INDEX
    Explanations

    references to vulnerability and danger in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quot
    -0.15
    ă
    -0.14
    ä¸ļ
    -0.14
    ahas
    -0.13
    ãĥ»ãĥ»ãĥ»↵↵
    -0.13
    headline
    -0.13
    vana
    -0.13
    owi
    -0.13
    subst
    -0.13
    .NotFound
    -0.13
    POSITIVE LOGITS
     hadn
    0.17
    ngoing
    0.17
    processable
    0.15
    ~=
    0.14
    currently
    0.14
     herself
    0.14
    chner
    0.14
    ãģĤãģ®
    0.13
    iasco
    0.13
    ipher
    0.13
    Act Density 0.004%

    No Known Activations