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

    Neuronpedia

    INDEX
    Explanations

    differences or contrasts between two entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures and patterns in sentence construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isure
    -0.63
     showc
    -0.62
    lift
    -0.62
    rox
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
     eruption
    -0.59
    ain
    -0.59
    Eva
    -0.59
     bucket
    -0.58
    ¬¼
    -0.58
    POSITIVE LOGITS
     however
    0.81
     ours
    0.68
     though
    0.67
    000
    0.64
     Seym
    0.64
     there
    0.64
    unin
    0.64
     whose
    0.63
    utherford
    0.63
    devices
    0.62
    Act Density 0.098%

    No Known Activations