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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alytics
    -0.17
    anova
    -0.16
    ish
    -0.16
    infeld
    -0.16
    ifth
    -0.15
    thora
    -0.14
    grams
    -0.14
    ãĥĥãĤ·ãĥ¥
    -0.14
     Lump
    -0.14
    æķ´
    -0.14
    POSITIVE LOGITS
     diret
    0.15
    /from
    0.14
    unes
    0.14
    orsk
    0.14
    orer
    0.14
    á»ı
    0.13
    HEL
    0.13
    iner
    0.13
     Orc
    0.13
    aped
    0.13
    Act Density 0.107%

    No Known Activations