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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and interaction

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to communication and actions taken by individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.79
    itialized
    -0.71
    bool
    -0.71
    Interstitial
    -0.70
    bda
    -0.68
     thats
    -0.66
    rection
    -0.64
    laughs
    -0.63
    nery
    -0.63
    fal
    -0.61
    POSITIVE LOGITS
     themselves
    1.51
     him
    1.18
     their
    1.08
    selves
    0.92
     Mr
    0.89
     Pruitt
    0.83
     DeVos
    0.82
    their
    0.80
     Tillerson
    0.76
     Moran
    0.73
    Act Density 0.517%

    No Known Activations