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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases that are very similar or near-identical to each other

    oai_token-act-pair · gpt-3.5-turbo

    terms related to similarity or sameness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rer
    -0.74
    âĵĺ
    -0.72
     Psychiat
    -0.70
     Brewer
    -0.69
    ASE
    -0.68
    akings
    -0.67
     Podesta
    -0.67
    erest
    -0.66
     Know
    -0.66
    Chart
    -0.66
    POSITIVE LOGITS
     twins
    1.14
     identical
    1.10
    quartered
    0.95
     twin
    0.87
    minded
    0.83
     copies
    0.82
    icut
    0.81
     sized
    0.80
    idious
    0.78
    NESS
    0.75
    Act Density 0.009%

    No Known Activations