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

    Neuronpedia

    INDEX
    Explanations

    words related to physical damage or destruction

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or word endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.73
     endowed
    -0.70
     accomp
    -0.65
     bare
    -0.65
     nont
    -0.64
     skilled
    -0.63
     bachelor
    -0.63
     conserv
    -0.61
     administ
    -0.61
     offic
    -0.60
    POSITIVE LOGITS
    claw
    1.05
    ings
    1.00
    down
    0.99
    bolt
    0.96
    ingly
    0.94
     Creek
    0.91
    hound
    0.91
    bite
    0.88
    weed
    0.87
    bol
    0.85
    Act Density 0.220%

    No Known Activations