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

    Neuronpedia

    INDEX
    Explanations

    instances of importance or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thora
    -0.17
    æŃ
    -0.14
    ccd
    -0.14
    onya
    -0.14
    hle
    -0.14
    vet
    -0.14
    iments
    -0.14
    structor
    -0.13
    monton
    -0.13
    bang
    -0.13
    POSITIVE LOGITS
     priority
    0.24
     part
    0.23
     concern
    0.23
     reality
    0.20
     necessity
    0.19
     constant
    0.19
     integral
    0.18
     factor
    0.18
    integral
    0.18
     breeze
    0.18
    Act Density 0.136%

    No Known Activations