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

    Neuronpedia

    INDEX
    Explanations

    words related to explosive or forceful actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to animal terms and related actions or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omes
    -0.72
    ystem
    -0.66
    rity
    -0.63
    ource
    -0.59
    ociation
    -0.56
    ynski
    -0.54
    sectional
    -0.53
    anse
    -0.53
     comply
    -0.53
     Generator
    -0.52
    POSITIVE LOGITS
    ishly
    1.14
    antly
    0.71
    ishes
    0.68
    rily
    0.67
    cially
    0.66
    lined
    0.65
    ently
    0.65
    kered
    0.64
    ped
    0.64
    uously
    0.62
    Act Density 0.155%

    No Known Activations