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

    Neuronpedia

    INDEX
    Explanations

    modal verbs, particularly those indicating potentiality or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æ¿
    -0.17
    ramer
    -0.14
    ertino
    -0.14
    ingleton
    -0.14
    swick
    -0.14
    ÙħاÙħ
    -0.14
    Manip
    -0.13
    isl
    -0.13
    umbo
    -0.13
    cone
    -0.13
    POSITIVE LOGITS
    ocs
    0.15
     DIR
    0.14
     Down
    0.14
    adden
    0.14
    orado
    0.14
    eff
    0.13
    Down
    0.13
    roj
    0.13
     Pou
    0.13
    rox
    0.13
    Act Density 0.982%

    No Known Activations