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

    Neuronpedia

    INDEX
    Explanations

    actions involving jumping or falling, typically from heights into water or other spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.16
    ked
    -0.16
    ναν
    -0.14
     nei
    -0.14
    bst
    -0.14
    emory
    -0.14
    borg
    -0.14
    .weapon
    -0.14
    uild
    -0.14
    enti
    -0.14
    POSITIVE LOGITS
     onto
    0.15
     Heights
    0.15
     heights
    0.15
    ptom
    0.14
     Shot
    0.14
    porto
    0.14
     landing
    0.14
    onto
    0.14
     rooft
    0.14
     height
    0.14
    Act Density 0.100%

    No Known Activations