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

    Neuronpedia

    INDEX
    Explanations

    actions involving jumping or falling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.16
    borg
    -0.15
    führ
    -0.15
    WindowSize
    -0.15
    ç·ł
    -0.14
    égor
    -0.14
     blockSize
    -0.14
    usters
    -0.14
    phia
    -0.14
    assis
    -0.14
    POSITIVE LOGITS
     onto
    0.18
     landing
    0.18
    onto
    0.17
    921
    0.15
    rack
    0.14
     Landing
    0.14
     Heights
    0.14
    Russ
    0.14
    into
    0.14
     height
    0.14
    Act Density 0.073%

    No Known Activations