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

    Neuronpedia

    INDEX
    Explanations

    keywords related to remnants or traces of objects or substances

    oai_token-act-pair · gpt-3.5-turbo

    words related to remains or evidence of something that has passed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.73
    otom
    -0.72
    yss
    -0.71
    Nich
    -0.68
     sophistic
    -0.66
    balanced
    -0.66
    sych
    -0.65
     cardinal
    -0.64
    MED
    -0.64
    bid
    -0.63
    POSITIVE LOGITS
     remnants
    1.16
     traces
    0.98
     remnant
    0.91
     Memories
    0.87
     thereof
    0.80
     scars
    0.79
     ashes
    0.79
    nants
    0.78
     lingering
    0.78
     Tracks
    0.77
    Act Density 0.031%

    No Known Activations