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

    Neuronpedia

    INDEX
    Explanations

    structures related to possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iek
    -0.15
    ior
    -0.14
    ocol
    -0.14
    517
    -0.14
    tah
    -0.14
    ubo
    -0.14
    their
    -0.13
    your
    -0.13
    že
    -0.13
    ikes
    -0.13
    POSITIVE LOGITS
     become
    0.20
    htags
    0.20
    htag
    0.19
     been
    0.19
    /h
    0.19
    /is
    0.19
     a
    0.18
     an
    0.17
     always
    0.17
     got
    0.16
    Act Density 0.081%

    No Known Activations