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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pload
    -0.90
    ulia
    -0.79
    ifully
    -0.70
    yip
    -0.68
    othy
    -0.68
    nesota
    -0.68
     Princ
    -0.68
    ammy
    -0.68
    amins
    -0.67
    iggs
    -0.67
    POSITIVE LOGITS
     ingrained
    1.16
     rooted
    1.09
     flawed
    0.98
     saddened
    0.95
     entrenched
    0.92
     indebted
    0.90
     intertwined
    0.90
     implicated
    0.90
     regret
    0.88
     wounded
    0.87
    Act Density 0.048%

    No Known Activations