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

    Neuronpedia

    INDEX
    Explanations

    descriptions of travel experiences and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.05
    3:0.27
    4:0.03
    5:0.25
    6:0.02
    7:0.08
    8:0.06
    9:0.02
    10:0.06
    11:0.03
    Negative Logits
    Distance
    -2.35
    duty
    -2.27
    distance
    -2.27
    raints
    -2.19
    entary
    -2.18
    rained
    -2.06
    ifle
    -2.04
    pread
    -2.01
    200000
    -2.01
     impulse
    -1.99
    POSITIVE LOGITS
     Nicaragua
    2.33
     Venezuela
    2.18
     paradise
    2.15
     Maurit
    2.14
     Canaan
    2.14
     Haiti
    2.13
     Honduras
    2.05
     Lanka
    2.02
     Lithuania
    2.01
     Americas
    2.01
    Act Density 0.446%

    No Known Activations