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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to geometry and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampo
    -0.15
    /bind
    -0.15
    rax
    -0.15
    phia
    -0.15
     forgiven
    -0.14
    raÄį
    -0.14
     Carlton
    -0.14
    _PRIV
    -0.14
    phalt
    -0.14
    duk
    -0.13
    POSITIVE LOGITS
    conv
    0.25
     Conv
    0.24
     comb
    0.22
    Conv
    0.22
    facet
    0.21
     aff
    0.21
    .Conv
    0.19
     poly
    0.18
     Fac
    0.18
     Vor
    0.18
    Act Density 0.024%

    No Known Activations