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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that describe similarities or resemblances

    oai_token-act-pair · gpt-3.5-turbo

    words related to similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alloc
    -0.85
    bra
    -0.72
    deal
    -0.72
    oard
    -0.71
    FT
    -0.71
    loads
    -0.69
    imb
    -0.69
    gard
    -0.68
    Published
    -0.68
    stra
    -0.67
    POSITIVE LOGITS
    lihood
    1.51
     likeness
    0.92
     ours
    0.79
     resembling
    0.75
     Tradable
    0.74
    lier
    0.72
    awei
    0.72
    ĸļ
    0.71
     resembles
    0.69
     twins
    0.69
    Act Density 0.034%

    No Known Activations