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

    Neuronpedia

    INDEX
    Explanations

    words associated with emotional or psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.19
    ardi
    -0.18
    adÃŃ
    -0.16
    entin
    -0.16
    éo
    -0.14
    ugas
    -0.14
    duk
    -0.14
    ган
    -0.14
    票
    -0.14
    oger
    -0.13
    POSITIVE LOGITS
    æĻ®éĢļ
    0.15
     Rupert
    0.14
     Feinstein
    0.14
     Invocation
    0.14
    letics
    0.14
    berger
    0.13
    berra
    0.13
    scroll
    0.13
    /layout
    0.13
    Scroll
    0.13
    Act Density 0.000%

    No Known Activations