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

    Neuronpedia

    INDEX
    Explanations

    terms related to visibility or the act of seeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erras
    -0.15
    DebugEnabled
    -0.15
    aux
    -0.15
    MPI
    -0.15
    .retry
    -0.14
    ablish
    -0.14
    vox
    -0.14
    thal
    -0.13
    amera
    -0.13
    .LA
    -0.13
    POSITIVE LOGITS
    arming
    0.22
    ÏĨÏħ
    0.17
    plet
    0.16
    ded
    0.16
    adem
    0.15
    bindings
    0.15
     Ded
    0.14
    ovel
    0.14
    .enums
    0.14
    wer
    0.14
    Act Density 0.007%

    No Known Activations