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

    Neuronpedia

    INDEX
    Explanations

    instances of the article 'a' and discuss its usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    witch
    -2.98
     Splash
    -2.93
     Fired
    -2.83
    wig
    -2.82
     Costume
    -2.79
     Attend
    -2.75
     Persona
    -2.72
     |--
    -2.71
     Witch
    -2.70
     Enchant
    -2.69
    POSITIVE LOGITS
     tc
    2.74
    iral
    2.67
     radial
    2.55
     referendum
    2.55
     viable
    2.54
     logic
    2.53
     reversible
    2.49
     angle
    2.47
    ndum
    2.45
    idges
    2.42
    Act Density 0.000%

    No Known Activations