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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Re" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¨
    -0.70
     Pebble
    -0.68
     buckle
    -0.67
    ãģĨ
    -0.66
     GEAR
    -0.66
     Beir
    -0.63
     CPR
    -0.63
     Icelandic
    -0.62
    åŃ
    -0.62
     Sammy
    -0.62
    POSITIVE LOGITS
    becca
    1.29
    levant
    1.28
    ceived
    1.24
    verend
    1.12
    asonable
    1.09
    venge
    1.09
    fect
    1.08
    venue
    1.08
    ggie
    1.07
    asons
    1.06
    Act Density 0.012%

    No Known Activations