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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and keywords related to deletion, control, and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ica
    -0.17
    oco
    -0.17
    å¬
    -0.16
    ICA
    -0.16
    ves
    -0.15
     Brilliant
    -0.15
    inge
    -0.15
    icas
    -0.15
    eff
    -0.14
    roll
    -0.14
    POSITIVE LOGITS
    boru
    0.15
    ruba
    0.15
     hra
    0.15
    erosis
    0.15
    iage
    0.14
     Mod
    0.14
    luv
    0.14
    Ïģιά
    0.14
     Platt
    0.14
    ãĤ¿ãĥ«
    0.14
    Act Density 0.006%

    No Known Activations