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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    immel
    -0.15
    halt
    -0.14
    _WM
    -0.14
    ÏģÏİ
    -0.14
    rink
    -0.13
    amon
    -0.13
    ķìĿ¸
    -0.13
     unto
    -0.13
    ught
    -0.13
    orses
    -0.13
    POSITIVE LOGITS
     reach
    0.57
     Reach
    0.40
    Reach
    0.39
    reach
    0.38
     range
    0.38
     sight
    0.37
     reaches
    0.35
     reached
    0.33
     reaching
    0.31
     reachable
    0.31
    Act Density 0.056%

    No Known Activations