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

    Neuronpedia

    INDEX
    Explanations

    key phrases and discussions regarding various topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pis
    -0.15
    اÙĤÙĦ
    -0.14
    åĤĻ
    -0.14
    ắc
    -0.13
    APO
    -0.13
    Äįást
    -0.13
     FORMAT
    -0.13
    qui
    -0.13
    á»ĵn
    -0.13
     دع
    -0.13
    POSITIVE LOGITS
     how
    0.31
     why
    0.26
    how
    0.22
     whether
    0.22
     ways
    0.21
     topic
    0.21
    å¦Ĥä½ķ
    0.20
     behalf
    0.20
     exactly
    0.19
     entitled
    0.18
    Act Density 0.205%

    No Known Activations