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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating methods or approaches to achieving outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INVAL
    -0.15
    Ñģен
    -0.15
    ëŀĢ
    -0.14
    xin
    -0.14
    urs
    -0.14
    AssignableFrom
    -0.13
    vrier
    -0.13
    rought
    -0.13
    شتÙĩ
    -0.13
    ำ
    -0.13
    POSITIVE LOGITS
     things
    0.28
    ward
    0.27
     they
    0.21
     mÃł
    0.21
     way
    0.20
     that
    0.20
     thing
    0.20
     we
    0.19
    (s
    0.19
     people
    0.18
    Act Density 0.035%

    No Known Activations