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

    Neuronpedia

    INDEX
    Explanations

    terms and references associated with literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eos
    -0.18
    venge
    -0.17
    een
    -0.17
    ors
    -0.16
    adows
    -0.16
    APA
    -0.16
    तर
    -0.16
    ÑģÑı
    -0.16
    uck
    -0.16
    steen
    -0.16
    POSITIVE LOGITS
    urgical
    0.21
    lle
    0.18
    /language
    0.18
    ature
    0.17
     critics
    0.17
    /art
    0.17
     critic
    0.17
     Crit
    0.16
    -minded
    0.16
    /music
    0.16
    Act Density 0.021%

    No Known Activations