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

    Neuronpedia

    INDEX
    Explanations

    references to time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oj
    -0.16
    abil
    -0.15
    aman
    -0.15
    ogan
    -0.15
     stabil
    -0.15
    dart
    -0.14
    eba
    -0.14
    jee
    -0.14
    ifold
    -0.14
     dispers
    -0.14
    POSITIVE LOGITS
     few
    0.24
     decade
    0.20
    few
    0.19
    ests
    0.18
     couple
    0.18
     vÃłi
    0.17
     several
    0.16
     Few
    0.16
    Few
    0.16
    reten
    0.15
    Act Density 0.061%

    No Known Activations