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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollo
    -0.19
    indow
    -0.16
    ÙĨØ´
    -0.16
    cid
    -0.16
     thừa
    -0.15
    GO
    -0.15
    .gs
    -0.14
    .grp
    -0.14
    ombine
    -0.14
    descriptor
    -0.14
    POSITIVE LOGITS
     toward
    0.15
    way
    0.15
     into
    0.15
    ward
    0.15
    eo
    0.14
    istrovstvÃŃ
    0.14
    247
    0.14
     back
    0.14
    .cgi
    0.14
    quam
    0.13
    Act Density 0.016%

    No Known Activations