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

    Neuronpedia

    INDEX
    Explanations

    similes describing resemblance to specific objects or environments

    oai_token-act-pair · gpt-3.5-turbo

    comparisons using the word 'like'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifi
    -0.79
    icians
    -0.73
    atel
    -0.73
    omics
    -0.71
    achus
    -0.70
    alf
    -0.70
    restling
    -0.69
    ilitary
    -0.69
    bell
    -0.69
    yna
    -0.69
    POSITIVE LOGITS
    lihood
    2.13
     tendencies
    1.04
     qualities
    0.97
     structures
    0.94
    liest
    0.92
     behaviors
    0.91
     structure
    0.90
     behavior
    0.89
    liness
    0.88
     substance
    0.88
    Act Density 0.035%

    No Known Activations