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

    Neuronpedia

    INDEX
    Explanations

    locations or positions inside something

    oai_token-act-pair · gpt-3.5-turbo

    locations or positions within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tackle
    -0.76
    enei
    -0.74
    ilaterally
    -0.72
    erenn
    -0.65
    ema
    -0.64
     pests
    -0.62
     habitats
    -0.61
     ancest
    -0.61
    pointers
    -0.60
     respectively
    -0.59
    POSITIVE LOGITS
    was
    0.81
     consists
    0.73
    pires
    0.72
     comprises
    0.69
     represents
    0.68
     corresponds
    0.67
     contains
    0.67
     reads
    0.66
     nutshell
    0.66
     varies
    0.66
    Act Density 0.473%

    No Known Activations