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

    Neuronpedia

    INDEX
    Explanations

    sentences that express existence or presence of entities and their states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stairs
    -0.69
     Pants
    -0.69
     Ambro
    -0.65
    ingham
    -0.64
    Newsletter
    -0.63
     TRUMP
    -0.63
     discont
    -0.60
     Wonderful
    -0.59
     Nicarag
    -0.58
    Mesh
    -0.58
    POSITIVE LOGITS
     wont
    0.90
     evidenced
    0.78
     actionGroup
    0.78
     often
    0.73
     attest
    0.70
     witnessed
    0.69
     previously
    0.69
     tend
    0.68
     tends
    0.67
    ãĥĩãĤ£
    0.66
    Act Density 0.129%

    No Known Activations