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

    Neuronpedia

    INDEX
    Explanations

    references to experts and authoritative voices in discussions about various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á¿ĸ
    -0.15
    ISTA
    -0.15
    Stick
    -0.14
    ovÃŃ
    -0.14
     perce
    -0.13
     apprec
    -0.13
    Äįem
    -0.13
    åłĤ
    -0.13
    uspend
    -0.13
     Stick
    -0.13
    POSITIVE LOGITS
     say
    0.24
     who
    0.23
     fear
    0.23
     worry
    0.22
     hope
    0.21
     estimate
    0.20
     across
    0.20
    /operators
    0.20
     believe
    0.20
     point
    0.20
    Act Density 0.116%

    No Known Activations