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

    Neuronpedia

    INDEX
    Explanations

    words related to strength and stability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eger
    -0.20
    esis
    -0.20
    fulness
    -0.17
    mscorlib
    -0.16
    aso
    -0.15
    carousel
    -0.15
    eba
    -0.15
    BOVE
    -0.15
    	Copyright
    -0.15
    erk
    -0.15
    POSITIVE LOGITS
    arity
    0.37
    ified
    0.36
    ifying
    0.36
    ification
    0.30
    ify
    0.28
    ifier
    0.27
    ifies
    0.27
    -solid
    0.26
    -state
    0.24
    ary
    0.23
    Act Density 0.021%

    No Known Activations