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

    Neuronpedia

    INDEX
    Explanations

    words related to connections or partnerships

    oai_token-act-pair · gpt-3.5-turbo

    references to ties or connections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.84
    issance
    -0.71
    TPPStreamerBot
    -0.68
    iation
    -0.67
     Wanted
    -0.65
    ocate
    -0.64
    ODY
    -0.63
    IVE
    -0.63
     Nights
    -0.63
    iveness
    -0.62
    POSITIVE LOGITS
     knot
    1.19
    breaker
    1.12
     knots
    1.08
    red
    1.07
    breakers
    1.07
    ged
    1.01
    tie
    0.98
    ging
    0.90
    break
    0.89
    breaks
    0.87
    Act Density 0.045%

    No Known Activations