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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments towards films or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.31
     zwar
    -0.27
     sice
    -0.26
     donc
    -0.25
     Therefore
    -0.24
    Therefore
    -0.23
     indeed
    -0.23
     daher
    -0.23
     accordingly
    -0.22
    çĶļèĩ³
    -0.22
    POSITIVE LOGITS
     also
    0.33
     soon
    0.30
     nevertheless
    0.29
     ALSO
    0.27
     nonetheless
    0.27
     still
    0.27
    also
    0.26
    åį»
    0.24
    Also
    0.24
     equally
    0.23
    Act Density 0.577%

    No Known Activations