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

    Neuronpedia

    INDEX
    Explanations

    instances of options and settings in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newState
    -0.44
     jadx
    -0.42
    phrag
    -0.40
     disant
    -0.39
    SOUNDBITE
    -0.39
    __((
    -0.38
    arangay
    -0.37
     '\\;'
    -0.37
    Cyfarwyddwr
    -0.35
    creva
    -0.35
    POSITIVE LOGITS
     dare
    0.57
    manage
    0.54
     dared
    0.53
     dares
    0.53
     Manage
    0.53
    Manage
    0.52
    aarrggbb
    0.52
     ModelExpression
    0.51
     defaultstate
    0.51
    opt
    0.48
    Act Density 0.145%

    No Known Activations