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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantitative changes or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.15
    igne
    -0.14
    ahu
    -0.14
    ãĥ¼ãĥ¬
    -0.13
    Ñģли
    -0.13
    aco
    -0.13
     sway
    -0.13
    echn
    -0.13
    remely
    -0.13
    ITTE
    -0.13
    POSITIVE LOGITS
     almost
    0.28
     leaps
    0.24
     nearly
    0.23
     factors
    0.23
     factor
    0.22
     as
    0.19
    almost
    0.19
     half
    0.18
     amounts
    0.18
     about
    0.17
    Act Density 0.026%

    No Known Activations