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

    Neuronpedia

    INDEX
    Explanations

    words related to public response and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uncio
    -0.15
    Interrupt
    -0.14
    ingleton
    -0.13
    omor
    -0.13
    yen
    -0.13
     numbered
    -0.13
    ))*(
    -0.13
    unkt
    -0.13
    λι
    -0.13
    Æ¡
    -0.12
    POSITIVE LOGITS
     push
    0.31
     fur
    0.28
     resistance
    0.26
    push
    0.25
     hue
    0.24
     opp
    0.24
     vit
    0.24
     criticism
    0.23
     blow
    0.23
     calls
    0.22
    Act Density 0.142%

    No Known Activations