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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to similarities or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'similar' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OST
    -0.80
    arden
    -0.78
     Drift
    -0.66
    UME
    -0.66
    oway
    -0.65
    Dispatch
    -0.64
     Lauderdale
    -0.63
    phasis
    -0.63
    live
    -0.63
     Brass
    -0.62
    POSITIVE LOGITS
     vein
    1.07
     minded
    0.98
    worldly
    0.98
    minded
    0.97
     sized
    0.96
     amounts
    0.93
    lihood
    0.92
     sentiments
    0.88
    MpServer
    0.84
     fate
    0.84
    Act Density 0.031%

    No Known Activations