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

    Neuronpedia

    INDEX
    Explanations

    references to socially critical or politically charged themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ROM
    -0.16
    ulumi
    -0.15
    ulos
    -0.14
    ajs
    -0.14
    ismet
    -0.13
    çIJ³
    -0.13
    competitive
    -0.13
    ascal
    -0.13
    interop
    -0.13
    ouro
    -0.13
    POSITIVE LOGITS
     political
    0.35
     social
    0.35
     message
    0.28
     Political
    0.27
     sat
    0.27
     Social
    0.27
     messages
    0.27
    political
    0.26
    social
    0.26
     politics
    0.24
    Act Density 0.425%

    No Known Activations