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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional release or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.19
    озв
    -0.16
    isa
    -0.15
    antz
    -0.15
     clums
    -0.15
    MESS
    -0.14
    ONUS
    -0.14
     spokes
    -0.14
    apore
    -0.14
    çĥ¦
    -0.14
    POSITIVE LOGITS
     knowing
    0.21
     resigned
    0.20
     satisfied
    0.19
     quick
    0.19
     look
    0.18
     sheep
    0.18
     drawn
    0.17
     Mona
    0.17
     glance
    0.17
     shr
    0.17
    Act Density 0.212%

    No Known Activations