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

    Neuronpedia

    INDEX
    Explanations

    specific references to job titles and roles in educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entering
    -0.15
    lauf
    -0.15
     being
    -0.14
     falling
    -0.14
     بÙĪدÙĨ
    -0.14
     approaching
    -0.14
    ields
    -0.13
     returning
    -0.13
    ãĥ¼ãĥĹ
    -0.13
     ид
    -0.13
    POSITIVE LOGITS
     so
    0.23
     signalling
    0.20
     hoping
    0.19
     signaling
    0.18
     at
    0.18
     promising
    0.17
     thinking
    0.17
     thanking
    0.16
     afterwards
    0.16
     urging
    0.15
    Act Density 0.014%

    No Known Activations