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

    Neuronpedia

    INDEX
    Explanations

    expressions related to awareness and familiarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghi
    -0.15
    Archive
    -0.15
    unds
    -0.15
    arton
    -0.14
     èIJ
    -0.14
    uja
    -0.14
    .Unsupported
    -0.13
    elman
    -0.13
    epend
    -0.13
    à¸Ļว
    -0.13
    POSITIVE LOGITS
     familiar
    0.69
     Fam
    0.57
     familiarity
    0.52
    amiliar
    0.51
     acquainted
    0.47
     aware
    0.45
    aware
    0.44
     awareness
    0.40
    -aware
    0.38
     Aware
    0.37
    Act Density 0.173%

    No Known Activations