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

    Neuronpedia

    INDEX
    Explanations

    personal references and possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roscope
    -0.13
    zew
    -0.12
     Jones
    -0.12
    newline
    -0.12
     prefixes
    -0.12
    minus
    -0.11
    prites
    -0.11
     pillars
    -0.11
     purposely
    -0.11
    Jones
    -0.11
    POSITIVE LOGITS
     Number
    0.68
     number
    0.68
    Number
    0.58
    number
    0.57
     NUMBER
    0.54
     numero
    0.53
     número
    0.51
    _number
    0.50
     Numero
    0.48
    -number
    0.47
    Act Density 0.086%

    No Known Activations