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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions, consequences, and effects

    oai_token-act-pair · gpt-3.5-turbo

    key actions or significant events that influence outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _>
    -0.82
     consulted
    -0.67
    yd
    -0.65
    cision
    -0.64
     retained
    -0.63
     supervised
    -0.63
     overseen
    -0.62
     wielding
    -0.60
     unaccompanied
    -0.60
     Referred
    -0.59
    POSITIVE LOGITS
     nerves
    0.85
     morale
    0.79
     viewers
    0.78
     me
    0.76
     us
    0.73
     reverber
    0.71
    notations
    0.69
     resonate
    0.65
     audiences
    0.65
    eur
    0.64
    Act Density 0.405%

    No Known Activations