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

    Neuronpedia

    INDEX
    Explanations

    contractions or possessive forms related to the subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateMap
    -0.17
    ffen
    -0.15
    etu
    -0.15
    borough
    -0.14
    adık
    -0.14
    enga
    -0.13
    yen
    -0.13
     avan
    -0.13
    bine
    -0.13
    alties
    -0.13
    POSITIVE LOGITS
     panel
    0.20
     Panel
    0.17
     panels
    0.16
     PANEL
    0.16
     IPS
    0.16
     Uniform
    0.15
    -panel
    0.15
     Panels
    0.15
     -
    0.14
    Panel
    0.14
    Act Density 0.000%

    No Known Activations