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

    Neuronpedia

    INDEX
    Explanations

    the word "of" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.09
    4:0.08
    5:0.09
    6:0.08
    7:0.09
    8:0.09
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     overs
    -2.93
     consumed
    -2.84
     <@
    -2.79
    isodes
    -2.75
    holiday
    -2.67
     enrol
    -2.64
    ishable
    -2.61
    ctory
    -2.58
    consumer
    -2.55
     billing
    -2.48
    POSITIVE LOGITS
    IPS
    3.21
     Centauri
    2.99
     Aluminum
    2.92
     Cyr
    2.92
     Vera
    2.92
     Ada
    2.88
     Lorenzo
    2.84
     graphene
    2.81
    antine
    2.81
     Icar
    2.76
    Act Density 0.000%

    No Known Activations