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

    Neuronpedia

    INDEX
    Explanations

    formatting or structural elements in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.16
    spy
    -0.16
     Bridges
    -0.16
    ometr
    -0.15
    ity
    -0.15
    antry
    -0.15
    tones
    -0.15
    eczy
    -0.15
    à¸Ľà¸£
    -0.14
    borg
    -0.14
    POSITIVE LOGITS
     Paradise
    0.16
     Valk
    0.15
    оÑĥ
    0.14
     denomination
    0.14
    /REC
    0.14
     Lever
    0.14
     club
    0.14
    _literals
    0.14
     comm
    0.13
     cow
    0.13
    Act Density 0.008%

    No Known Activations