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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desires and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.66
    jspx
    -0.63
    ADELPHIA
    -0.59
     retenir
    -0.57
     ostrich
    -0.57
    Ouch
    -0.56
    Maestro
    -0.55
     ARGUMENT
    -0.55
     encomp
    -0.54
     Exactos
    -0.54
    POSITIVE LOGITS
     want
    1.03
     wanted
    0.96
     wants
    0.93
     wanting
    0.93
     desire
    0.89
     Wanted
    0.85
     Want
    0.82
     WANT
    0.82
    want
    0.79
    Want
    0.78
    Act Density 0.377%

    No Known Activations