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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "can't help" followed by verbs or pronouns indicating involuntary actions or emotions, such as "feeling", "smile", "notice", and "staring"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "help" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.73
    Safe
    -0.70
    lore
    -0.70
    Home
    -0.67
    oven
    -0.66
    âĢ¢âĢ¢
    -0.64
    LAN
    -0.64
    LOS
    -0.62
    ledged
    -0.61
    yz
    -0.60
    POSITIVE LOGITS
     noticing
    1.07
     wondering
    0.90
     feeling
    0.89
     grinning
    0.86
     but
    0.85
     smiling
    0.82
     laughing
    0.81
     imagining
    0.80
     slipping
    0.78
    but
    0.76
    Act Density 0.026%

    No Known Activations