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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trustworthy news sources

    oai_token-act-pair · gpt-3.5-turbo

    questions and expressions of interest or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.78
     eroded
    -0.76
    hene
    -0.72
    isons
    -0.69
     decap
    -0.68
     reneg
    -0.68
     estranged
    -0.68
     unaccount
    -0.68
    acle
    -0.66
     dismantled
    -0.66
    POSITIVE LOGITS
    Disclaimer
    0.95
    âĺħ
    0.90
    âĿ
    0.87
    VOL
    0.85
    Brow
    0.84
    Click
    0.84
    Mouse
    0.84
    Ye
    0.83
    GU
    0.82
    Subscribe
    0.82
    Act Density 0.257%

    No Known Activations