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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members or loved ones in distressing situations

    oai_token-act-pair · gpt-3.5-turbo

    references to families of victims in tragic circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.77
    oven
    -0.71
    iron
    -0.70
    esm
    -0.68
    ussen
    -0.66
    essen
    -0.66
    anke
    -0.65
    ocular
    -0.65
    esian
    -0.64
    assembly
    -0.64
    POSITIVE LOGITS
     deceased
    1.22
     murdered
    0.97
     slain
    0.96
     aborted
    0.85
     kidnapped
    0.83
     abducted
    0.80
     martyr
    0.78
     convicted
    0.78
     stricken
    0.78
     victims
    0.78
    Act Density 0.084%

    No Known Activations