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

    Neuronpedia

    INDEX
    Explanations

    phrases related to existential questions about self and consciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quote
    -0.72
     FANT
    -0.66
    plex
    -0.62
    jl
    -0.62
     Anyway
    -0.62
    ibe
    -0.61
     Firstly
    -0.61
    Gil
    -0.60
     Annotations
    -0.60
    sites
    -0.60
    POSITIVE LOGITS
     likewise
    0.84
    maxwell
    0.68
    aeus
    0.67
     inferior
    0.66
     subtract
    0.66
     opposite
    0.64
     withdraw
    0.64
     similarly
    0.63
     nominate
    0.62
     nonexistent
    0.61
    Act Density 0.281%

    No Known Activations