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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.05
    2:0.11
    3:0.06
    4:0.05
    5:0.08
    6:0.04
    7:0.07
    8:0.12
    9:0.07
    10:0.06
    11:0.12
    Negative Logits
     subscript
    -2.32
    standard
    -1.85
    fter
    -1.81
    attribute
    -1.78
    ivalent
    -1.76
    illance
    -1.71
    ティ
    -1.70
    enser
    -1.67
    イ
    -1.66
    displayText
    -1.65
    POSITIVE LOGITS
     Pil
    1.93
     Roh
    1.85
     Sonny
    1.85
     Glen
    1.82
     Vale
    1.79
     Bye
    1.76
     Manor
    1.75
     Ashe
    1.74
     Lyon
    1.72
     PJ
    1.71
    Act Density 0.000%

    No Known Activations