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

    Neuronpedia

    INDEX
    Explanations

    references to physical substances or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eg
    -0.21
    ed
    -0.17
    ors
    -0.17
    es
    -0.17
    ess
    -0.17
    amilia
    -0.17
    ote
    -0.16
    kara
    -0.15
    enso
    -0.15
    ORS
    -0.15
    POSITIVE LOGITS
    istic
    0.26
    ized
    0.23
    ity
    0.22
    izing
    0.22
    ize
    0.21
    è´¨
    0.21
    質
    0.21
    UnderTest
    0.20
    istically
    0.19
    ien
    0.19
    Act Density 0.029%

    No Known Activations