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

    Neuronpedia

    INDEX
    Explanations

    references to creating and implementing plans or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aru
    -0.19
    deaux
    -0.16
    .gdx
    -0.16
    omen
    -0.15
    hani
    -0.15
    jmu
    -0.15
    ĸī
    -0.15
    ermen
    -0.14
    oved
    -0.14
    ombo
    -0.14
    POSITIVE LOGITS
     plan
    0.24
     plans
    0.18
    ooth
    0.17
    -plan
    0.17
     Plan
    0.16
    æĸ¹æ¡Ī
    0.16
    (plan
    0.15
    illes
    0.15
     Disclosure
    0.15
    ighton
    0.15
    Act Density 0.173%

    No Known Activations