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

    Neuronpedia

    INDEX
    Explanations

    words related to harbors and harboring

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harbors or harboring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eds
    -0.81
    cious
    -0.80
     millenn
    -0.70
    etition
    -0.68
    Downloadha
    -0.65
    iane
    -0.62
    onymous
    -0.62
    onym
    -0.62
    isable
    -0.61
    acia
    -0.61
    POSITIVE LOGITS
    bors
    0.95
    ttes
    0.90
     harbor
    0.89
     harb
    0.83
     harbour
    0.81
    masters
    0.79
    bour
    0.78
     Spit
    0.77
    lot
    0.77
    lash
    0.76
    Act Density 0.027%

    No Known Activations