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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and phrases that suggest additional information or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roys
    -0.17
    alars
    -0.14
    hlas
    -0.13
    ain
    -0.13
    enance
    -0.13
    enza
    -0.13
    angan
    -0.13
     اÙĦثاÙĦØ«
    -0.12
    ainen
    -0.12
    ena
    -0.12
    POSITIVE LOGITS
     etc
    0.30
    etc
    0.26
     others
    0.24
     many
    0.22
    ãģªãģ©
    0.20
     çŃī
    0.19
    others
    0.19
    çŃī
    0.19
    Others
    0.18
     among
    0.17
    Act Density 0.098%

    No Known Activations