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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or actions described in the first person

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "I" and related personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loops
    -0.69
     decoration
    -0.68
     Haku
    -0.66
     dies
    -0.63
     2048
    -0.62
    INGTON
    -0.62
     stagnation
    -0.61
     Ezekiel
    -0.59
    Ĥİ
    -0.59
     reversible
    -0.58
    POSITIVE LOGITS
    ldon
    0.99
    xtap
    0.92
    ñ
    0.87
    cade
    0.80
    emen
    0.80
    adr
    0.80
    opia
    0.79
    aci
    0.79
    arag
    0.79
    atri
    0.78
    Act Density 0.322%

    No Known Activations