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

    Neuronpedia

    INDEX
    Explanations

    phrases related to securing or binding things

    oai_token-act-pair · gpt-3.5-turbo

    actions related to constraints or binding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fm
    -0.60
    llor
    -0.58
     mL
    -0.57
    merce
    -0.56
     tending
    -0.56
    perty
    -0.56
     VIDEOS
    -0.55
    bm
    -0.55
    grave
    -0.55
    FUL
    -0.54
    POSITIVE LOGITS
     knots
    1.00
     together
    0.94
     onto
    0.93
     securely
    0.89
     knot
    0.85
    together
    0.83
     seams
    0.82
     thereto
    0.81
     dots
    0.75
    ovan
    0.72
    Act Density 0.205%

    No Known Activations