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

    Neuronpedia

    INDEX
    Explanations

    themes related to cultural expressions and trends in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĦ
    -0.16
    SSERT
    -0.15
    plit
    -0.15
     split
    -0.14
    AMERA
    -0.14
     ghost
    -0.14
     Split
    -0.14
    ussen
    -0.13
    -split
    -0.13
     çĶŁåij½åij¨æľŁ
    -0.13
    POSITIVE LOGITS
     rebels
    0.28
     rebel
    0.28
     rebell
    0.27
     rebellion
    0.27
     hip
    0.25
     alternative
    0.25
    punk
    0.24
     underground
    0.23
     sub
    0.23
     Alternative
    0.23
    Act Density 0.182%

    No Known Activations