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

    Neuronpedia

    INDEX
    Explanations

    words ending with the suffix "ives"

    oai_token-act-pair · gpt-4-turbo

    words related to empowerment and strength

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "lives" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deviation
    -0.68
    Els
    -0.65
     variance
    -0.63
    Lord
    -0.62
    Gi
    -0.59
     trivial
    -0.59
    Mah
    -0.57
    utherford
    -0.56
     distracting
    -0.56
    adra
    -0.55
    POSITIVE LOGITS
    ives
    1.16
    ynthesis
    0.84
    hops
    0.81
    hots
    0.80
    ipel
    0.76
    rov
    0.76
    hyde
    0.76
    ived
    0.76
    IVE
    0.76
    dropping
    0.76
    Act Density 0.015%

    No Known Activations