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

    Neuronpedia

    INDEX
    Explanations

    mentions of atoms or atomic properties

    oai_token-act-pair · gpt-3.5-turbo

    references to atoms and atomic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PE
    -0.82
    don
    -0.79
    Cu
    -0.77
    dk
    -0.76
     Fargo
    -0.75
    HCR
    -0.75
    Calling
    -0.73
    CV
    -0.73
    DON
    -0.73
    VICE
    -0.71
    POSITIVE LOGITS
     atom
    1.33
     Atom
    1.21
     atoms
    1.03
    atom
    0.99
    ctrl
    0.92
     bomb
    0.90
    atomic
    0.89
    izer
    0.89
    izers
    0.89
    alyst
    0.88
    Act Density 0.005%

    No Known Activations