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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to performance metrics and content-driven strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -covered
    -0.16
    919
    -0.15
     assail
    -0.15
    ngr
    -0.14
    -quality
    -0.14
    ross
    -0.14
    -encoded
    -0.14
    ifa
    -0.14
    pping
    -0.13
    ossa
    -0.13
    POSITIVE LOGITS
     cent
    0.61
     orient
    0.59
     oriented
    0.52
    cent
    0.51
     Orient
    0.51
    orient
    0.48
    -cent
    0.47
     Cent
    0.46
    oriented
    0.46
     centered
    0.45
    Act Density 0.284%

    No Known Activations