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

    Neuronpedia

    INDEX
    Explanations

    comparisons using similes

    oai_token-act-pair · gpt-3.5-turbo

    similes and metaphors comparing different objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.69
     dubious
    -0.63
     conspicuous
    -0.62
     Judicial
    -0.62
    Ħ¢
    -0.62
     concess
    -0.62
     emph
    -0.61
     unspecified
    -0.61
    ?????-
    -0.60
    andra
    -0.60
    POSITIVE LOGITS
    itaire
    0.76
    mouse
    0.75
     sponge
    0.71
     unto
    0.71
    paste
    0.70
     magnet
    0.67
     meets
    0.65
    pour
    0.64
     ants
    0.63
     microscope
    0.62
    Act Density 0.401%

    No Known Activations