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

    Neuronpedia

    INDEX
    Explanations

    hyphenated phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant delays or issues in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.85
     Borders
    -0.84
     Scrib
    -0.84
     Phi
    -0.81
     Indigo
    -0.79
    ulhu
    -0.77
     Survivors
    -0.76
     ROCK
    -0.75
     Shooter
    -0.74
     Exile
    -0.73
    POSITIVE LOGITS
    needed
    1.22
    sized
    1.17
    anticipated
    1.15
    awaited
    1.14
    recent
    1.13
    equipped
    1.13
    powerful
    1.12
    earned
    1.10
    produced
    1.09
    sounding
    1.08
    Act Density 0.043%

    No Known Activations