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

    Neuronpedia

    INDEX
    Explanations

    words related to comparison and similarity

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to similarity and resemblance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GBT
    -0.71
     Swed
    -0.71
    GW
    -0.70
    earchers
    -0.68
    Thor
    -0.68
    WARE
    -0.64
    hooting
    -0.63
    Republic
    -0.62
    Iss
    -0.62
     Guides
    -0.62
    POSITIVE LOGITS
    tones
    0.80
     Attribution
    0.76
     whatsoever
    0.74
     resembling
    0.73
    thood
    0.69
     semblance
    0.69
     vis
    0.68
     foothold
    0.66
    etic
    0.66
     monopoly
    0.65
    Act Density 0.632%

    No Known Activations