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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making something more secure or tense

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanisms of constraint or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itable
    -0.97
    estine
    -0.90
    amon
    -0.85
    ouf
    -0.84
    kt
    -0.79
     Lowry
    -0.79
    rums
    -0.78
    grounds
    -0.78
    uin
    -0.76
    itia
    -0.75
    POSITIVE LOGITS
     tightened
    0.95
     wrench
    0.95
     clamp
    0.93
     tighten
    0.89
     screws
    0.87
    driver
    0.83
     bolts
    0.82
     tightening
    0.81
     tension
    0.78
     straps
    0.75
    Act Density 0.034%

    No Known Activations