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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate societal instability and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.15
    etch
    -0.15
     æ·
    -0.15
    orne
    -0.14
    ODO
    -0.14
    rna
    -0.14
    olas
    -0.14
    ookies
    -0.14
    icer
    -0.14
    леÑĩ
    -0.13
    POSITIVE LOGITS
     itself
    0.16
    -wide
    0.16
    .userInteractionEnabled
    0.14
    ittings
    0.14
    -relative
    0.14
    225
    0.14
     Girlfriend
    0.14
    osaic
    0.14
    <<<<<<<<
    0.13
    .Errors
    0.13
    Act Density 0.358%

    No Known Activations