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

    Neuronpedia

    INDEX
    Explanations

    details related to accidents and collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corridors
    -0.19
     Contributor
    -0.15
    582
    -0.15
    onaut
    -0.15
    riba
    -0.15
     skins
    -0.14
     Bowl
    -0.14
    ussen
    -0.14
     Floors
    -0.13
     bowl
    -0.13
    POSITIVE LOGITS
     trees
    0.32
     Trees
    0.28
    trees
    0.27
     posts
    0.26
     tree
    0.26
    Trees
    0.26
     lam
    0.25
     sign
    0.24
     fence
    0.23
     poles
    0.23
    Act Density 0.262%

    No Known Activations