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

    Neuronpedia

    INDEX
    Explanations

    structured data formats or programming constructs related to policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adele
    -0.16
    storybook
    -0.15
     Nullable
    -0.14
     hung
    -0.14
    osu
    -0.13
     SOCK
    -0.13
    dzi
    -0.13
    antee
    -0.13
    _levels
    -0.13
    Rejected
    -0.13
    POSITIVE LOGITS
    ÄĽj
    0.18
    abus
    0.15
    946
    0.15
    ture
    0.14
    athers
    0.14
    ħn
    0.14
    _txn
    0.14
    ":[{↵
    0.14
    å±Ĭ
    0.14
     rally
    0.14
    Act Density 0.063%

    No Known Activations