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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and dynamic interactions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igli
    -0.16
    ër
    -0.16
    éru
    -0.15
    ientos
    -0.15
    .Compile
    -0.15
    ħn
    -0.14
     зм
    -0.14
    _mD
    -0.14
    ilim
    -0.14
     Digest
    -0.14
    POSITIVE LOGITS
     y
    0.29
     кÑĢи
    0.28
     cry
    0.26
     scre
    0.25
     Scre
    0.24
     SC
    0.22
    åı«
    0.22
     yell
    0.22
     how
    0.22
     cried
    0.22
    Act Density 0.208%

    No Known Activations