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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umba
    -0.16
    smith
    -0.15
     acomp
    -0.15
     shim
    -0.14
     Preconditions
    -0.14
    Forge
    -0.14
     Noel
    -0.14
     Beled
    -0.14
    ted
    -0.14
    eda
    -0.14
    POSITIVE LOGITS
    Å®
    0.15
    .postMessage
    0.15
    имв
    0.15
    گرد
    0.14
     Barton
    0.14
    ãĥ¼ãĥĨ
    0.14
    725
    0.13
    365
    0.13
     PUB
    0.13
     Mim
    0.13
    Act Density 0.135%

    No Known Activations