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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     encomp
    -1.72
     ftre
    -1.60
     ftu
    -1.55
     apprehen
    -1.50
     tranf
    -1.50
     fuf
    -1.48
     vns
    -1.47
     guarante
    -1.45
     purcha
    -1.44
     fays
    -1.43
    POSITIVE LOGITS
    Alas
    1.19
     Alas
    1.18
     minus
    1.09
     mighty
    1.07
    minus
    0.98
     Mighty
    0.92
    Mighty
    0.87
    tachment
    0.84
    Personendaten
    0.82
    mighty
    0.81
    Act Density 0.354%

    No Known Activations