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

    Neuronpedia

    INDEX
    Explanations

    actions and expressions of intention or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UINT
    -0.15
     sırada
    -0.14
     Moreno
    -0.14
    lm
    -0.14
    gre
    -0.14
    itus
    -0.13
    afi
    -0.13
    sis
    -0.13
    ultipart
    -0.13
    oriously
    -0.13
    POSITIVE LOGITS
    lrt
    0.17
     pant
    0.16
    reas
    0.16
    isque
    0.15
     Impl
    0.14
    ror
    0.14
    olib
    0.14
    iore
    0.13
    pec
    0.13
    ippers
    0.13
    Act Density 0.396%

    No Known Activations