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

    Neuronpedia

    INDEX
    Explanations

    terms related to fellowships and academic affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gil
    -0.19
    bone
    -0.18
    oola
    -0.17
    baz
    -0.17
    okers
    -0.16
    iginal
    -0.15
    ophil
    -0.15
    yclic
    -0.15
    ÏĦα
    -0.15
     Voll
    -0.14
    POSITIVE LOGITS
    ships
    0.39
    ship
    0.27
    shipping
    0.25
    hips
    0.22
    SHIP
    0.22
    hip
    0.22
    chaft
    0.20
    ows
    0.20
    infeld
    0.16
    iesen
    0.16
    Act Density 0.006%

    No Known Activations