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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful physical action or defeat

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crush" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appropri
    -0.82
    vernment
    -0.70
    gard
    -0.67
    erville
    -0.67
    iggins
    -0.67
    gewater
    -0.66
    adapt
    -0.66
    endment
    -0.66
    ciation
    -0.66
    ouf
    -0.65
    POSITIVE LOGITS
     crush
    1.14
     Crush
    1.02
     crushing
    1.01
     earthqu
    0.90
     crushed
    0.86
     stomp
    0.79
     spoil
    0.75
    oidal
    0.75
    bum
    0.74
     fracture
    0.70
    Act Density 0.011%

    No Known Activations