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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to comparative situations or scenarios involving teams or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tackle
    -0.82
    undrum
    -0.76
    clair
    -0.76
    ftime
    -0.76
    abel
    -0.75
    pin
    -0.73
    thood
    -0.71
    wen
    -0.70
    Ireland
    -0.69
    aphael
    -0.69
    POSITIVE LOGITS
     ones
    1.54
     rest
    1.24
     perpetrators
    1.20
     slightest
    1.15
     bosses
    1.07
     remainder
    1.07
     attackers
    1.06
     masses
    1.06
     consequences
    1.05
     authorities
    1.03
    Act Density 0.479%

    No Known Activations