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

    Neuronpedia

    INDEX
    Explanations

    spatial relationships and proximity expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occo
    -0.15
    ķìĿ¸
    -0.15
    iske
    -0.14
    halt
    -0.14
    ovo
    -0.13
     Jeg
    -0.13
    éné
    -0.13
    aid
    -0.13
    \Eloquent
    -0.13
    _WM
    -0.13
    POSITIVE LOGITS
     reach
    0.54
     range
    0.48
     sight
    0.47
    range
    0.37
     Range
    0.36
    reach
    0.36
     Reach
    0.36
     RANGE
    0.35
    -range
    0.35
     view
    0.35
    Act Density 0.095%

    No Known Activations