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

    Neuronpedia

    INDEX
    Explanations

    mention of words related to atomic or subatomic particles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to atomic and nuclear concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fargo
    -0.85
    nir
    -0.75
    cific
    -0.74
    atche
    -0.72
    VICE
    -0.69
     Angeles
    -0.68
    shire
    -0.67
    Guard
    -0.66
    affer
    -0.64
    ersen
    -0.64
    POSITIVE LOGITS
     atoms
    0.89
    ysis
    0.88
     atom
    0.88
     bomb
    0.85
    ctrl
    0.83
     latt
    0.83
     nucle
    0.81
     physicist
    0.80
    atomic
    0.79
     clocks
    0.79
    Act Density 0.043%

    No Known Activations