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

    Neuronpedia

    INDEX
    Explanations

    instances of prompts or transitions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.86
    amorph
    -0.70
    icone
    -0.69
     witnesses
    -0.65
    ModLoader
    -0.65
    uyomi
    -0.65
    uments
    -0.64
    aeus
    -0.63
    adoes
    -0.63
     alleged
    -0.63
    POSITIVE LOGITS
    follow
    0.64
    cour
    0.64
    bnb
    0.62
     consider
    0.60
    league
    0.59
    optional
    0.58
    galitarian
    0.57
     [+
    0.57
    ital
    0.57
    econom
    0.56
    Act Density 0.129%

    No Known Activations