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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing quantifiable comparisons or degrees, especially involving "much" and "more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crowley
    -0.84
    DockStyle
    -0.83
    Affiliations
    -0.78
     HttpHeaders
    -0.72
    e
    -0.71
    Reno
    -0.71
    providedIn
    -0.70
     createSprite
    -0.69
     Krause
    -0.69
    UITableViewCell
    -0.68
    POSITIVE LOGITS
     MUCH
    1.26
     much
    1.06
    Mucho
    1.04
    much
    1.04
    Much
    1.01
     Much
    0.97
    mucho
    0.89
     mucha
    0.84
     dużo
    0.82
     Muck
    0.82
    Act Density 0.099%

    No Known Activations