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

    Neuronpedia

    INDEX
    Explanations

    specific movie titles

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.80
    staking
    -0.76
     irrespective
    -0.75
     territ
    -0.75
    fully
    -0.74
     compuls
    -0.73
     accordingly
    -0.71
     owing
    -0.70
     consecut
    -0.67
    cum
    -0.67
    POSITIVE LOGITS
     Beginning
    0.90
     Mouth
    0.85
     Mountains
    0.85
     Future
    0.83
     Heights
    0.83
     Past
    0.81
     Throne
    0.80
     Blind
    0.79
     Clintons
    0.78
     Balance
    0.78
    Act Density 0.403%

    No Known Activations