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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating ongoing or past states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Directed
    -0.16
    deaux
    -0.15
     categor
    -0.15
    Sharper
    -0.15
     Hoy
    -0.15
    eya
    -0.15
    arro
    -0.14
     Orient
    -0.14
     issued
    -0.14
    swick
    -0.14
    POSITIVE LOGITS
     studied
    0.22
     explored
    0.21
     investigated
    0.20
     discussed
    0.19
     covered
    0.18
     known
    0.18
     thoroughly
    0.18
     documented
    0.18
    fully
    0.17
     examined
    0.17
    Act Density 0.146%

    No Known Activations