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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.74
     Yourself
    -0.65
    ufact
    -0.64
     Stuff
    -0.61
    theless
    -0.60
    hide
    -0.58
    ancial
    -0.57
     Creature
    -0.57
    Ton
    -0.56
    arsity
    -0.56
    POSITIVE LOGITS
     anyway
    0.68
    phas
    0.68
     anyways
    0.66
     unres
    0.62
    opian
    0.59
    âĶĢâĶĢâĶĢâĶĢ
    0.58
     terminating
    0.57
     it
    0.57
     boils
    0.56
    galitarian
    0.56
    Act Density 0.037%

    No Known Activations