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

    Neuronpedia

    INDEX
    Explanations

    phrases that compare objects or situations using similes or metaphors

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and similes involving physical objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAT
    -0.67
    amina
    -0.64
    arios
    -0.62
    merce
    -0.62
    omas
    -0.61
    cipled
    -0.61
    amas
    -0.60
    emin
    -0.60
     concess
    -0.60
     conspicuous
    -0.60
    POSITIVE LOGITS
     circa
    0.89
     unto
    0.80
     except
    0.76
     minus
    0.72
     meets
    0.72
     dipped
    0.71
     doll
    0.71
    .:
    0.69
    !:
    0.68
     nailed
    0.67
    Act Density 0.411%

    No Known Activations