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

    Neuronpedia

    INDEX
    Explanations

    the word "tangible" and words related to tangible things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to tangible or concrete concepts and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.78
    giene
    -0.77
    ften
    -0.73
    cker
    -0.72
    oly
    -0.71
    afa
    -0.70
    selection
    -0.68
    ologies
    -0.68
    oan
    -0.67
    selected
    -0.67
    POSITIVE LOGITS
     tangible
    1.14
    isable
    0.92
     conclud
    0.88
     manifestation
    0.87
    çIJ
    0.84
     intangible
    0.83
     defic
    0.82
    zx
    0.80
    izable
    0.80
    angible
    0.79
    Act Density 0.011%

    No Known Activations