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

    Neuronpedia

    INDEX
    Explanations

    references to "defense" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erer
    -0.17
    hey
    -0.16
    ish
    -0.15
    ãĥ«ãĤ¯
    -0.15
    oras
    -0.15
    iquid
    -0.15
    essian
    -0.15
    ings
    -0.15
    icious
    -0.14
    affe
    -0.14
    POSITIVE LOGITS
    less
    0.26
     against
    0.23
    lessness
    0.23
     Against
    0.21
     mechanisms
    0.20
     mechanism
    0.20
    /off
    0.19
    against
    0.19
     contractor
    0.19
    LESS
    0.18
    Act Density 0.031%

    No Known Activations