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

    Neuronpedia

    INDEX
    Explanations

    expressions related to geographical distances and directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    89
    -0.17
    63
    -0.17
    92
    -0.16
    65
    -0.15
    94
    -0.15
    64
    -0.15
    issen
    -0.15
    bris
    -0.15
    47
    -0.14
    84
    -0.14
    POSITIVE LOGITS
    500
    0.27
    800
    0.23
    600
    0.22
    700
    0.22
    750
    0.20
    400
    0.19
    900
    0.18
     kil
    0.17
    300
    0.17
     several
    0.16
    Act Density 0.068%

    No Known Activations