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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ordinal rankings or sequencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allas
    -0.15
    /goto
    -0.15
    achen
    -0.14
    IMA
    -0.14
    /entities
    -0.14
    etal
    -0.13
    jaw
    -0.13
    ltre
    -0.13
    åħħ
    -0.13
    _closure
    -0.13
    POSITIVE LOGITS
     three
    0.22
     several
    0.19
     two
    0.19
     many
    0.17
    three
    0.16
    ä¸ī
    0.15
    two
    0.15
     ä¸ī
    0.15
    rin
    0.15
    lant
    0.15
    Act Density 0.048%

    No Known Activations