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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rankings or performance statistics in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.84
    otin
    -0.83
    conservancy
    -0.82
    sect
    -0.81
    itely
    -0.80
    inarily
    -0.80
    icz
    -0.78
     oun
    -0.76
    ersive
    -0.76
    ãĥ¢
    -0.75
    POSITIVE LOGITS
     Appears
    1.38
     Includes
    1.31
     Also
    1.30
     Comes
    1.26
     Uses
    1.24
     Cannot
    1.24
     Contains
    1.17
     Requires
    1.17
     Shows
    1.15
     Needs
    1.13
    Act Density 0.242%

    No Known Activations