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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating choices or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Dk
    -0.19
    chet
    -0.17
    -fontawesome
    -0.15
    ogl
    -0.15
    erdale
    -0.14
    ãĤ¤ãĥ¤
    -0.14
    riger
    -0.14
    eus
    -0.14
     NÄĽm
    -0.13
    isle
    -0.13
    POSITIVE LOGITS
     Wing
    0.16
     option
    0.16
    textfield
    0.16
     Option
    0.15
     wings
    0.14
     wing
    0.14
    erno
    0.14
    aleigh
    0.14
    ixin
    0.14
    éri
    0.14
    Act Density 0.106%

    No Known Activations