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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of probability or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aph
    -0.15
    axter
    -0.15
    Ïĥμ
    -0.14
    iasm
    -0.14
    ipi
    -0.14
    elson
    -0.14
    iou
    -0.14
     коп
    -0.14
    adar
    -0.14
    ception
    -0.14
    POSITIVE LOGITS
    illas
    0.19
     possibly
    0.17
     ds
    0.17
    Poss
    0.16
    hart
    0.16
     end
    0.16
     cert
    0.16
     swims
    0.15
    orig
    0.15
     function
    0.15
    Act Density 0.049%

    No Known Activations