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

    Neuronpedia

    INDEX
    Explanations

    terms related to adaptation and adjustment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.73
    ItemGroup
    -0.72
     betweenstory
    -0.72
    zeera
    -0.68
     Mayweather
    -0.64
    issão
    -0.63
     Whitney
    -0.63
    iverr
    -0.63
    lebo
    -0.61
    yanka
    -0.61
    POSITIVE LOGITS
     Adapt
    2.11
     adapt
    2.10
     adapts
    2.09
     adapted
    2.03
     adaptation
    2.03
     adapting
    2.00
    adapt
    1.94
     Adaptation
    1.93
     Adap
    1.90
    Adap
    1.89
    Act Density 0.089%

    No Known Activations