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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases related to capabilities and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rupa
    -0.15
    cakes
    -0.14
     only
    -0.14
     Lah
    -0.14
     Boeh
    -0.14
     place
    -0.14
     higher
    -0.14
    dep
    -0.14
    cake
    -0.13
     extremism
    -0.13
    POSITIVE LOGITS
     usual
    0.17
    strict
    0.15
    antro
    0.15
    ervo
    0.15
     any
    0.15
    اÙĤع
    0.14
    Strict
    0.14
    ouri
    0.14
    cope
    0.14
    COPE
    0.14
    Act Density 0.091%

    No Known Activations