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

    Neuronpedia

    INDEX
    Explanations

    architectural features and design elements in a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chet
    -0.17
    hort
    -0.15
    неÑģ
    -0.15
    ÑĨвеÑĤ
    -0.15
    eshire
    -0.15
     Cabinet
    -0.14
    odial
    -0.14
     Bowen
    -0.14
     fence
    -0.14
     sublist
    -0.14
    POSITIVE LOGITS
     ceiling
    0.51
     ceilings
    0.49
     Ceiling
    0.44
     поÑĤол
    0.40
     overhead
    0.34
     vault
    0.32
     ceil
    0.31
    -ce
    0.30
     raft
    0.30
    ceil
    0.30
    Act Density 0.077%

    No Known Activations