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

    Neuronpedia

    INDEX
    Explanations

    entities related to controversy or conflict, such as political figures or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quantity
    -0.76
    ãĥĺ
    -0.69
    nings
    -0.65
    LOCK
    -0.65
    ãĤ±
    -0.64
    itive
    -0.63
     ellipt
    -0.61
    ainment
    -0.60
     Collider
    -0.59
     Valkyrie
    -0.59
    POSITIVE LOGITS
     alike
    0.99
     whom
    0.98
    who
    0.93
    sembly
    0.82
    vae
    0.77
    ©¶æ¥µ
    0.75
    conserv
    0.71
    oots
    0.71
    agna
    0.70
    opes
    0.69
    Act Density 0.824%

    No Known Activations