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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases expressing discovery, realization, or opinion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.75
    isoft
    -0.72
    idium
    -0.67
    apeake
    -0.66
    chief
    -0.63
    PHOTOS
    -0.63
    IPS
    -0.62
    opausal
    -0.61
    vous
    -0.60
    icro
    -0.60
    POSITIVE LOGITS
     myself
    0.98
     oneself
    0.95
     fault
    0.94
     yourself
    0.89
     ourselves
    0.88
     themselves
    0.87
     inspiration
    0.86
     himself
    0.79
     it
    0.79
     herself
    0.79
    Act Density 0.054%

    No Known Activations