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

    Neuronpedia

    INDEX
    Explanations

    mentions of screws and their properties

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     houſe
    -1.21
     ſtate
    -1.18
     Efq
    -1.16
     Majefty
    -1.15
     pleaſure
    -1.09
    ſelf
    -1.09
     myſelf
    -1.08
    .";
    -1.05
     Jefus
    -1.00
    ſelves
    -0.98
    POSITIVE LOGITS
     screws
    1.50
     Screw
    1.48
     screw
    1.37
    screw
    1.36
    Screw
    1.32
     Screws
    1.32
     screwing
    1.05
     screwed
    1.03
    scre
    0.93
     skru
    0.84
    Act Density 0.007%

    No Known Activations