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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating certainty or strong belief

    oai_token-act-pair · gpt-3.5-turbo

    assertions of certainty or strong belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agus
    -0.68
    ueless
    -0.68
    ilaterally
    -0.67
    itiz
    -0.67
     Chains
    -0.65
    achi
    -0.65
    eways
    -0.64
    ithing
    -0.64
    ocket
    -0.63
    rites
    -0.62
    POSITIVE LOGITS
     whatsoever
    1.19
     ABOUT
    0.87
     about
    0.79
     mark
    0.65
    about
    0.64
    XM
    0.61
     About
    0.60
     entertained
    0.58
    ãĤª
    0.58
     haunt
    0.58
    Act Density 0.036%

    No Known Activations