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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "going to," indicating future intentions or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horus
    -0.70
    aments
    -0.68
    ullah
    -0.68
    ament
    -0.66
    essor
    -0.64
    uminati
    -0.61
    essa
    -0.60
    peria
    -0.60
    stra
    -0.59
    chell
    -0.59
    POSITIVE LOGITS
     nowhere
    0.89
     overboard
    0.83
     downhill
    0.81
    ãĥ£
    0.75
     viral
    0.75
     extinct
    0.74
    ober
    0.73
     bankrupt
    0.71
    ggle
    0.71
     Commando
    0.70
    Act Density 0.054%

    No Known Activations