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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſch
    -0.67
     iſt
    -0.65
    ſelf
    -0.65
    RenderAtEndOf
    -0.63
     ſta
    -0.63
     poffe
    -0.62
     onBind
    -0.60
     pleaſure
    -0.59
    StoryboardSegue
    -0.57
    bootstrapcdn
    -0.56
    POSITIVE LOGITS
     get
    0.80
     kinda
    0.74
     freaking
    0.73
     gonna
    0.73
     fuckin
    0.72
     just
    0.71
     freakin
    0.71
     got
    0.70
     freaked
    0.68
     fucking
    0.68
    Act Density 1.061%

    No Known Activations