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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proximity and convenience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uling
    -0.16
    одо
    -0.14
    _MP
    -0.14
    ampton
    -0.14
    istring
    -0.13
    ampler
    -0.13
     коÑĢм
    -0.13
    ázd
    -0.13
    (AL
    -0.13
    atar
    -0.13
    POSITIVE LOGITS
     stones
    0.32
     stone
    0.28
     minute
    0.28
     short
    0.27
     minutes
    0.26
     hop
    0.25
    -minute
    0.25
    stones
    0.24
     steps
    0.22
     blocks
    0.22
    Act Density 0.033%

    No Known Activations