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

    Neuronpedia

    INDEX
    Explanations

    descriptions of transformation or change from one role to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of transformation or change in identity or role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ording
    -0.84
    enegger
    -0.72
    intent
    -0.68
    ussen
    -0.67
    rack
    -0.67
    è¦ļéĨĴ
    -0.67
    Story
    -0.67
    cdn
    -0.66
    capacity
    -0.66
    ities
    -0.65
    POSITIVE LOGITS
    bum
    0.69
     sideways
    0.68
    \\\\\\\\
    0.66
     into
    0.66
    AAA
    0.65
     Prairie
    0.63
    terday
    0.63
    ©¶æ
    0.63
    \\\\\\\\\\\\\\\\
    0.63
     srf
    0.62
    Act Density 0.024%

    No Known Activations