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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to customization or modification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adjustability and flexibility in design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    src
    -0.99
    ynthesis
    -0.88
    achu
    -0.87
    sic
    -0.84
    ouls
    -0.83
    ys
    -0.82
    orr
    -0.81
    esville
    -0.81
    keeper
    -0.80
    insk
    -0.80
    POSITIVE LOGITS
     reversible
    0.98
     wooden
    0.92
     removable
    0.92
    theless
    0.92
     adjustable
    0.88
     decorative
    0.86
     triangular
    0.83
     magnetic
    0.83
     curved
    0.83
     modular
    0.83
    Act Density 0.027%

    No Known Activations