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

    Neuronpedia

    INDEX
    Explanations

    comparisons highlighting differences or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Unlike" to highlight contrasting comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anut
    -0.73
    è¦ļéĨĴ
    -0.69
    ander
    -0.65
    alian
    -0.65
     Peninsula
    -0.64
    ells
    -0.64
    acht
    -0.64
    arc
    -0.63
    eding
    -0.62
    oca
    -0.61
    POSITIVE LOGITS
    lihood
    1.37
    yip
    1.02
    ly
    0.84
    etheless
    0.83
    entimes
    0.81
    liest
    0.80
    eatures
    0.80
     minded
    0.78
    minded
    0.76
    stellar
    0.74
    Act Density 0.005%

    No Known Activations