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

    Neuronpedia

    INDEX
    Explanations

    phrases describing something at its extreme or peak state

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the extreme qualities or states of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arov
    -0.66
    ela
    -0.65
    bender
    -0.64
    icio
    -0.64
    icia
    -0.63
    dit
    -0.61
    FTWARE
    -0.61
    ipel
    -0.61
     Uriel
    -0.61
    ski
    -0.61
    POSITIVE LOGITS
     simplest
    1.41
     inception
    1.30
     infancy
    1.30
     finest
    1.27
     weakest
    1.17
     widest
    1.16
     fullest
    1.14
     essence
    1.12
     busiest
    1.06
     darkest
    1.04
    Act Density 0.071%

    No Known Activations