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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific qualities or conditions

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to quality and condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ravings
    -0.89
     icons
    -0.85
    brids
    -0.84
    ammers
    -0.81
    apses
    -0.79
    appings
    -0.79
    rists
    -0.79
    uties
    -0.78
    Tags
    -0.77
     rebels
    -0.77
    POSITIVE LOGITS
     manner
    1.23
     context
    1.12
     nutshell
    1.06
     vein
    1.02
     guise
    1.01
     fashion
    0.97
     Perspective
    0.87
     format
    0.87
     hurry
    0.86
     standpoint
    0.86
    Act Density 0.255%

    No Known Activations