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

    Neuronpedia

    INDEX
    Explanations

    phrases or words containing the substring "fre"

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to freedom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gravity
    -0.71
     direction
    -0.66
     liking
    -0.61
     Conrad
    -0.59
     dummy
    -0.59
     naming
    -0.59
     torment
    -0.57
     billing
    -0.57
     recommendation
    -0.57
     fate
    -0.56
    POSITIVE LOGITS
    estyle
    1.49
    eways
    1.34
    aky
    1.33
    eware
    1.24
    aked
    1.24
    tted
    1.23
    emen
    1.21
    ighter
    1.19
    eworld
    1.19
    aks
    1.18
    Act Density 0.019%

    No Known Activations