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

    Neuronpedia

    INDEX
    Explanations

    the word "this" in various contexts throughout the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucht
    -0.16
     passion
    -0.15
     ones
    -0.15
    hai
    -0.14
     Sob
    -0.14
     Ones
    -0.14
     suspect
    -0.14
    ator
    -0.14
    hip
    -0.13
    inv
    -0.13
    POSITIVE LOGITS
     æ¹
    0.19
    utsch
    0.16
    illes
    0.15
    apes
    0.15
    csi
    0.15
    eroon
    0.15
    ameda
    0.15
    opis
    0.14
    -spe
    0.14
    oud
    0.14
    Act Density 0.055%

    No Known Activations