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

    Neuronpedia

    INDEX
    Explanations

    instances of trends in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    . 
    -0.64
     iVar
    -0.64
    rrggbb
    -0.61
    GOTREF
    -0.61
    roring
    -0.60
    UIControlState
    -0.60
    ■
    -0.59
     BrowserModule
    -0.59
    omiast
    -0.59
     незавершена
    -0.59
    POSITIVE LOGITS
     trend
    0.86
     sensitive
    0.73
     freedom
    0.72
    trend
    0.70
    Instructions
    0.69
     tendance
    0.68
    Freedom
    0.68
     tendency
    0.68
     probation
    0.66
     Trend
    0.66
    Act Density 0.109%

    No Known Activations