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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ships and specific ship-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly related to ships and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.96
    éĥ
    -0.79
    è£
    -0.77
    åº
    -0.77
    å·
    -0.76
    è»
    -0.75
    PLIED
    -0.75
    代
    -0.75
    ITED
    -0.74
     quo
    -0.72
    POSITIVE LOGITS
     Ago
    0.93
     Away
    0.90
    waters
    0.84
    shall
    0.84
     Thing
    0.83
     Knock
    0.82
     Deal
    0.82
     Off
    0.82
    downs
    0.81
     Offer
    0.81
    Act Density 0.040%

    No Known Activations