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

    Neuronpedia

    INDEX
    Explanations

    words related to tapping or physical hitting

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of edible product or ingredient related to tapioca

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Valkyrie
    -0.71
     Monstrous
    -0.70
    xual
    -0.67
     AMERICA
    -0.67
    Downloadha
    -0.66
    ============
    -0.65
     CVE
    -0.64
    anchester
    -0.61
    士
    -0.59
     Camel
    -0.59
    POSITIVE LOGITS
    acity
    1.00
    eless
    0.86
    istry
    0.85
    leness
    0.85
    ering
    0.85
    rop
    0.84
    roots
    0.84
    rist
    0.82
    eful
    0.81
    deck
    0.80
    Act Density 0.031%

    No Known Activations