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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing worry or interest in a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingers
    -0.87
     Bom
    -0.71
    obs
    -0.68
     slick
    -0.67
    essed
    -0.66
    ools
    -0.64
    exc
    -0.63
    sung
    -0.63
    ortunately
    -0.63
    amples
    -0.63
    POSITIVE LOGITS
    wart
    0.96
    warts
    0.96
     trolling
    0.87
     Concern
    0.85
     concern
    0.82
    enza
    0.80
     concerns
    0.76
    lessly
    0.75
    Parents
    0.71
    atives
    0.70
    Act Density 0.034%

    No Known Activations