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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTV
    -0.75
    cius
    -0.75
    mere
    -0.74
    Reporting
    -0.73
    SourceFile
    -0.67
    sett
    -0.66
    NS
    -0.65
    sav
    -0.64
    checking
    -0.64
    cart
    -0.64
    POSITIVE LOGITS
     be
    1.02
     explode
    0.96
     stick
    0.93
     hell
    0.93
     lose
    0.92
     need
    0.92
     try
    0.92
     get
    0.92
     make
    0.89
     unleash
    0.87
    Act Density 0.080%

    No Known Activations