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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating creation, development, or alteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĽn
    -0.15
    \Migration
    -0.15
    atter
    -0.15
    umped
    -0.14
     MERCHANTABILITY
    -0.14
     fg
    -0.14
    rrha
    -0.14
    rál
    -0.14
    ãĥ³ãĥij
    -0.14
    OrNil
    -0.13
    POSITIVE LOGITS
    etur
    0.17
    -spacing
    0.14
     ler
    0.14
    iram
    0.14
    /generated
    0.14
    emo
    0.14
    ory
    0.14
     اÙĦØŃÙĦ
    0.14
    eries
    0.13
    aily
    0.13
    Act Density 0.332%

    No Known Activations