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

    Neuronpedia

    INDEX
    Explanations

    terms related to defense and obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Boom
    -0.16
    ung
    -0.16
    æĸ
    -0.15
    etting
    -0.15
    itr
    -0.15
    aman
    -0.14
    oleÄį
    -0.14
    usz
    -0.14
    afe
    -0.14
    ohn
    -0.14
    POSITIVE LOGITS
     resistance
    0.17
    egl
    0.16
    gon
    0.16
     against
    0.16
    cock
    0.15
    ocker
    0.15
    lex
    0.15
    chg
    0.14
    obox
    0.14
     cock
    0.14
    Act Density 0.234%

    No Known Activations