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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being at risk

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential hazards or dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anche
    -0.81
    rix
    -0.76
    elf
    -0.67
    ript
    -0.65
    ovy
    -0.65
     headquartered
    -0.64
    ao
    -0.63
    ann
    -0.62
    erent
    -0.62
    MX
    -0.61
    POSITIVE LOGITS
    ħĭ
    0.84
     endanger
    0.84
    angering
    0.75
     undermin
    0.74
     casualties
    0.72
     schizophren
    0.70
     Survive
    0.68
     dism
    0.68
     pitfalls
    0.68
     starvation
    0.67
    Act Density 0.022%

    No Known Activations