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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of ladders and related terms in the context of safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulis
    -0.15
    anske
    -0.15
    abbo
    -0.14
    kinson
    -0.14
    <quote
    -0.14
    acho
    -0.14
    idges
    -0.14
    ÛĮÙĨÚ¯
    -0.14
    ÂłPS
    -0.14
     Verfüg
    -0.14
    POSITIVE LOGITS
     ransom
    0.17
    .sul
    0.14
    è¼
    0.14
    सर
    0.14
    å®ĭä½ĵ
    0.14
    STEM
    0.13
    íļ¨
    0.13
    :c
    0.13
     c
    0.13
     censor
    0.13
    Act Density 0.052%

    No Known Activations