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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to strength and stability

    oai_token-act-pair · gpt-3.5-turbo

    the concept of solidity and stability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.82
    NetMessage
    -0.70
    clipse
    -0.69
     wrongly
    -0.67
    plugins
    -0.67
     wisely
    -0.66
    llor
    -0.64
     medd
    -0.64
     Peninsula
    -0.63
    erity
    -0.63
    POSITIVE LOGITS
    ified
    1.44
    ifying
    1.30
    GoldMagikarp
    1.24
    ifies
    1.14
    ification
    1.11
    arity
    1.04
    ify
    0.97
    ifier
    0.96
    ifiers
    0.94
    ity
    0.92
    Act Density 0.024%

    No Known Activations