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

    Neuronpedia

    INDEX
    Explanations

    instances of "the" and words indicating intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.57
    enterOuterAlt
    -0.48
     idea
    -0.42
     gimmick
    -0.42
    цезда
    -0.40
    Possibility
    -0.40
     urma
    -0.39
    occurrence
    -0.39
    idea
    -0.39
     Possibility
    -0.39
    POSITIVE LOGITS
     things
    0.93
     many
    0.79
     dingen
    0.77
     kinds
    0.74
     steder
    0.69
     tools
    0.68
     countless
    0.67
    many
    0.64
     decisions
    0.63
     technologies
    0.61
    Act Density 0.561%

    No Known Activations