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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word 'der'

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "der."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetti
    -0.75
     Dragonbound
    -0.75
    ELS
    -0.72
    YA
    -0.67
     Starr
    -0.66
    Crash
    -0.65
    zzi
    -0.65
    Reviewer
    -0.63
    enthal
    -0.63
    DragonMagazine
    -0.62
    POSITIVE LOGITS
    isively
    1.15
    iving
    1.08
    isive
    0.95
    mal
    0.94
    ider
    0.91
    anged
    0.87
    ision
    0.84
    iding
    0.80
    ided
    0.78
    oder
    0.77
    Act Density 0.008%

    No Known Activations