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

    Neuronpedia

    INDEX
    Explanations

    the recurring phrase "welcome to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iddi
    -0.17
    hetto
    -0.15
    ertools
    -0.15
    pole
    -0.15
    .GroupLayout
    -0.15
    наÑĢ
    -0.15
    IBC
    -0.14
    паÑĤ
    -0.14
    nodoc
    -0.14
    tet
    -0.14
    POSITIVE LOGITS
    jective
    0.17
    isex
    0.15
    ÏĦεÏģ
    0.14
     Pivot
    0.14
     Punch
    0.14
     punch
    0.14
     intr
    0.14
    èĥ
    0.14
    ck
    0.14
     Henderson
    0.14
    Act Density 0.014%

    No Known Activations