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

    Neuronpedia

    INDEX
    Explanations

    the letter 'J'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.09
    4:0.08
    5:0.07
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     Morton
    -2.71
     compost
    -2.68
     Native
    -2.65
     leaf
    -2.65
     arrow
    -2.49
     prox
    -2.44
     pancreat
    -2.43
     relocation
    -2.43
     Parks
    -2.43
     Hole
    -2.40
    POSITIVE LOGITS
    maxwell
    3.11
    jri
    2.90
    assault
    2.90
    ieri
    2.85
    nikov
    2.82
    "]=>
    2.81
    Crime
    2.76
    nai
    2.70
    encer
    2.69
    ukong
    2.67
    Act Density 0.000%

    No Known Activations