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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lint
    -0.16
     discretion
    -0.16
    scal
    -0.14
    opsis
    -0.14
    Malloc
    -0.14
    ãĤ©
    -0.14
     tid
    -0.14
     доÑģ
    -0.14
     backdrop
    -0.14
    itecture
    -0.14
    POSITIVE LOGITS
     position
    0.38
     state
    0.38
    state
    0.30
     Position
    0.28
    position
    0.28
     positions
    0.28
     rut
    0.28
     bind
    0.27
     mood
    0.27
    Position
    0.25
    Act Density 0.106%

    No Known Activations