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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to beginnings or initiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.56
     Witherspoon
    -0.55
     woll
    -0.49
     commenced
    -0.49
     supposed
    -0.48
     Coimbra
    -0.48
     Anastasia
    -0.48
     petra
    -0.48
     surfact
    -0.48
     combineReducers
    -0.47
    POSITIVE LOGITS
     start
    0.99
     go
    0.93
     الحره
    0.77
    findpost
    0.75
     stop
    0.74
    start
    0.74
     drop
    0.69
    go
    0.65
     send
    0.64
     cabo
    0.64
    Act Density 0.082%

    No Known Activations