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

    Neuronpedia

    INDEX
    Explanations

    words related to importance and influence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the significance and effectiveness of roles or actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andals
    -0.86
    classes
    -0.85
    events
    -0.82
     Units
    -0.82
    codes
    -0.80
     Classes
    -0.79
    hops
    -0.79
    laws
    -0.77
    skirts
    -0.76
    facts
    -0.76
    POSITIVE LOGITS
     foothold
    1.02
     role
    0.92
     impression
    0.89
     stance
    0.88
     berth
    0.84
     angle
    0.82
     burden
    0.78
     charge
    0.77
     dive
    0.77
     effort
    0.77
    Act Density 0.229%

    No Known Activations