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

    Neuronpedia

    INDEX
    Explanations

    negative spatial or geographical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.04
    4:0.04
    5:0.03
    6:0.46
    7:0.07
    8:0.03
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
    arcity
    -1.63
    ��
    -1.41
    akeru
    -1.37
    bably
    -1.35
     aggreg
    -1.33
    76561
    -1.32
    apesh
    -1.32
    oké
    -1.31
    itionally
    -1.31
    acci
    -1.31
    POSITIVE LOGITS
    backer
    1.48
    rings
    1.33
    angle
    1.32
     Banks
    1.31
    bones
    1.30
     confines
    1.29
    chel
    1.29
    middle
    1.25
    roth
    1.25
    Snake
    1.25
    Act Density 0.010%

    No Known Activations