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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions containing the prepositions "to" and "the" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uther
    -0.15
    ingham
    -0.14
    min
    -0.14
    lec
    -0.14
    ollapsed
    -0.14
    agt
    -0.13
    hole
    -0.13
    ¶Į
    -0.13
    ãģĵãĤĵãģ«
    -0.13
    hen
    -0.13
    POSITIVE LOGITS
    ocz
    0.17
    onus
    0.15
    swers
    0.15
    ŀæĢ§
    0.15
    zelf
    0.15
    ARSE
    0.14
    .chapter
    0.14
    arlar
    0.14
    iya
    0.14
    mue
    0.14
    Act Density 0.044%

    No Known Activations