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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "there" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endphp
    -0.63
    userdetails
    -0.60
    ειν
    -0.60
     propOrder
    -0.56
     CreateTagHelper
    -0.54
     GenerationType
    -0.51
    classpath
    -0.51
    AndEndTag
    -0.49
     ErrIntOverflow
    -0.49
    bigcap
    -0.48
    POSITIVE LOGITS
    of
    0.64
     are
    0.63
     vary
    0.56
     exist
    0.54
     tend
    0.53
     Vikipedi
    0.50
     have
    0.47
    __':
    0.47
    ForType
    0.46
    pflich
    0.46
    Act Density 0.143%

    No Known Activations