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

    Neuronpedia

    INDEX
    Explanations

    concepts related to free speech and censorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     double
    -0.15
    ierge
    -0.14
     оÑĩ
    -0.14
     tele
    -0.14
    .transfer
    -0.14
     Compound
    -0.14
    ouz
    -0.14
    /tasks
    -0.14
    _IPV
    -0.13
    ozo
    -0.13
    POSITIVE LOGITS
     prov
    0.17
     Freedom
    0.16
     stap
    0.16
    åĻ
    0.16
     freedom
    0.16
    xon
    0.15
    Freedom
    0.15
    inspace
    0.15
     shutting
    0.14
     censorship
    0.14
    Act Density 0.135%

    No Known Activations