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

    Neuronpedia

    INDEX
    Explanations

    scientific or technical terms related to data analysis or research, such as 'predictions', 'assumptions', and 'measurements'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to predictions and assumptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.76
    culus
    -0.63
    onel
    -0.62
     mobility
    -0.62
    steamapps
    -0.62
     nerve
    -0.61
    bia
    -0.60
    avis
    -0.60
     bonding
    -0.58
    riot
    -0.58
    POSITIVE LOGITS
     regarding
    1.01
    mith
    0.97
     concerning
    0.97
    uggest
    0.96
    ayers
    0.89
     pertaining
    0.85
    ensical
    0.80
    hooting
    0.76
    ynthesis
    0.74
    ynt
    0.74
    Act Density 0.165%

    No Known Activations