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

    Neuronpedia

    INDEX
    Explanations

    the phrases or sentences indicating future action or intention

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "going to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTV
    -0.80
    Reporting
    -0.77
    Pres
    -0.77
    cart
    -0.72
    sett
    -0.67
    mere
    -0.66
    Login
    -0.65
    NS
    -0.64
    SourceFile
    -0.64
    Previous
    -0.64
    POSITIVE LOGITS
     be
    0.94
     stick
    0.88
     regress
    0.87
     try
    0.85
     need
    0.84
     lose
    0.84
     get
    0.83
     behave
    0.82
     hell
    0.81
     explode
    0.80
    Act Density 0.077%

    No Known Activations