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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.81
    LOCK
    -0.81
    DragonMagazine
    -0.77
    INESS
    -0.74
    RL
    -0.74
    9999
    -0.73
    MODE
    -0.71
    AMA
    -0.71
    ress
    -0.70
    fml
    -0.70
    POSITIVE LOGITS
     behalf
    1.31
    etime
    1.14
    shore
    0.96
    coming
    0.92
    eness
    0.91
    eday
    0.90
    boarding
    0.89
     steroids
    0.88
     occasion
    0.87
    lined
    0.85
    Act Density 0.212%

    No Known Activations