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

    Neuronpedia

    INDEX
    Explanations

    dialogue that conveys emotional expressions and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.15
    MESS
    -0.14
    umper
    -0.14
    Ñģли
    -0.14
    undef
    -0.13
    ĥ
    -0.13
    .uc
    -0.13
    brains
    -0.13
    emoth
    -0.13
    zc
    -0.13
    POSITIVE LOGITS
     grunt
    0.25
     knowing
    0.24
     satisfied
    0.24
     smirk
    0.23
     grin
    0.23
     puzzled
    0.23
     sigh
    0.22
     disgusted
    0.22
     resigned
    0.22
     glare
    0.22
    Act Density 0.161%

    No Known Activations