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

    Neuronpedia

    INDEX
    Explanations

    positive and negative reactions, feedback, and support related terms

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public reactions or responses, particularly positive and negative feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bis
    -0.69
    tein
    -0.64
     conserv
    -0.64
     lookout
    -0.63
     navig
    -0.61
     gamb
    -0.61
     pocket
    -0.60
     negotiator
    -0.60
     Fix
    -0.59
     Sit
    -0.59
    POSITIVE LOGITS
     acclaim
    1.01
     disapproval
    0.97
     ridicule
    0.91
     applause
    0.87
     outcry
    0.84
     condemnation
    0.81
    soType
    0.79
     backlash
    0.78
    lash
    0.77
     disbel
    0.77
    Act Density 0.427%

    No Known Activations