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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with explosive events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipe
    -0.18
    irm
    -0.15
    ripp
    -0.13
    ills
    -0.13
     Beast
    -0.13
    .scalablytyped
    -0.13
    nez
    -0.13
    ##_
    -0.13
    ought
    -0.13
    ling
    -0.13
    POSITIVE LOGITS
    ìĿĮìĿĦ
    0.17
    frog
    0.15
    starter
    0.15
    /exp
    0.14
    ué
    0.14
     thá»ĭ
    0.14
    agram
    0.14
    erin
    0.14
    urgeon
    0.13
    orde
    0.13
    Act Density 0.062%

    No Known Activations