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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people finding themselves in various situations

    oai_token-act-pair · gpt-3.5-turbo

    reflexive pronouns indicating a sense of personal involvement or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.70
    ulton
    -0.67
    imedia
    -0.67
    omy
    -0.66
    idine
    -0.64
    IQ
    -0.64
    asus
    -0.63
    idy
    -0.63
    izes
    -0.62
     Tycoon
    -0.62
    POSITIVE LOGITS
     trapped
    0.86
     wondering
    0.86
     stranded
    0.83
     needing
    0.83
     wanting
    0.81
     besieged
    0.80
     embroiled
    0.79
     stuck
    0.79
     immersed
    0.78
    hler
    0.77
    Act Density 0.029%

    No Known Activations