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

    Neuronpedia

    INDEX
    Explanations

    phrases related to someone's name followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "hes" as part of various words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.74
     congress
    -0.64
     spokes
    -0.63
     collusion
    -0.62
     coff
    -0.62
    vernment
    -0.62
     Yemeni
    -0.60
    inally
    -0.59
     collaboration
    -0.59
     Belgium
    -0.58
    POSITIVE LOGITS
    apeake
    1.15
    creen
    1.05
    terday
    1.05
    omen
    0.94
    esville
    0.93
    hes
    0.92
    imus
    0.91
    hire
    0.86
    anes
    0.86
    ter
    0.86
    Act Density 0.006%

    No Known Activations