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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or providing solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interpersonal relationships and emotional support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.66
    arij
    -0.59
     overest
    -0.58
     McDonnell
    -0.56
     underestimate
    -0.56
     Barcl
    -0.55
     Interior
    -0.53
     Originally
    -0.53
     Nit
    -0.53
     Rear
    -0.53
    POSITIVE LOGITS
    .'"
    0.94
    )).
    0.92
    ?".
    0.92
    '."
    0.85
    ))))
    0.85
    !".
    0.85
    )."
    0.82
    ]."
    0.81
    ?'"
    0.79
    '.
    0.77
    Act Density 1.566%

    No Known Activations