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

    Neuronpedia

    INDEX
    Explanations

    references to vertical or horizontal orientations or alignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.16
    lum
    -0.16
    edium
    -0.15
    lore
    -0.15
    ensem
    -0.14
    ellery
    -0.14
    edin
    -0.14
    elier
    -0.14
    ickle
    -0.14
    pering
    -0.14
    POSITIVE LOGITS
    -vertical
    0.21
    -horizontal
    0.20
    mente
    0.20
    ity
    0.18
    idad
    0.18
    ities
    0.17
    -axis
    0.17
    igo
    0.17
    polit
    0.16
    izing
    0.16
    Act Density 0.028%

    No Known Activations