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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection and management

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éŃĶ
    -0.68
    hov
    -0.65
     Loren
    -0.63
    ESE
    -0.60
    ---------
    -0.57
    :(
    -0.57
    iciary
    -0.57
     Doodle
    -0.57
    :'
    -0.56
     Stronghold
    -0.56
    POSITIVE LOGITS
    rogen
    1.01
    rogens
    0.99
     therefore
    0.98
     consequently
    0.89
    rew
    0.87
     possibly
    0.81
    /
    0.81
     thus
    0.76
     redistributed
    0.74
     thereby
    0.74
    Act Density 0.398%

    No Known Activations