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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.19
    ioso
    -0.15
    obil
    -0.15
    Overrides
    -0.14
    oser
    -0.14
    ajas
    -0.14
     sidel
    -0.14
     bre
    -0.14
    cks
    -0.14
     tslib
    -0.14
    POSITIVE LOGITS
    efa
    0.21
    ache
    0.18
    recent
    0.16
    _recent
    0.16
     recent
    0.16
    ACHE
    0.15
     likely
    0.15
    ToMany
    0.15
    ecká
    0.15
    owing
    0.14
    Act Density 0.087%

    No Known Activations