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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize issues or concerns relating to various topics, particularly in legal or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ron
    -0.15
    ãĥ¼ãĥĬ
    -0.15
    vr
    -0.14
    ic
    -0.14
    uded
    -0.14
    olog
    -0.13
    dt
    -0.13
    Ø©
    -0.13
     /*č↵
    -0.13
    orem
    -0.13
    POSITIVE LOGITS
     matters
    0.21
    undler
    0.15
    -Core
    0.15
     Matters
    0.14
     matter
    0.14
    emark
    0.14
    tember
    0.14
    lament
    0.14
    atter
    0.14
     finances
    0.14
    Act Density 0.111%

    No Known Activations