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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positivity and favorable outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to positive outcomes or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oths
    -0.85
    ngth
    -0.82
    atum
    -0.81
    puter
    -0.81
    ptin
    -0.79
    appings
    -0.76
    adr
    -0.73
    alian
    -0.72
    hid
    -0.72
    neys
    -0.72
    POSITIVE LOGITS
     reinforcement
    1.02
     outlook
    0.96
     outcome
    0.95
     vib
    0.94
     feedback
    0.94
     affirm
    0.89
     affirmation
    0.86
     appraisal
    0.85
     outcomes
    0.84
     attitude
    0.84
    Act Density 0.041%

    No Known Activations