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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific research and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.16
    ìĥĿ
    -0.15
    æ®Ĭ
    -0.14
    NX
    -0.14
    imonial
    -0.14
    iste
    -0.14
     Dirty
    -0.13
    ruba
    -0.13
    anders
    -0.13
     generation
    -0.13
    POSITIVE LOGITS
     Ca
    0.15
     Arth
    0.14
    ipay
    0.14
     оÑĤп
    0.14
    ahren
    0.14
    castle
    0.14
    anon
    0.13
     Rosenberg
    0.13
     surpr
    0.13
    raz
    0.13
    Act Density 0.025%

    No Known Activations