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

    Neuronpedia

    INDEX
    Explanations

    words related to entertainment or hosting activities

    oai_token-act-pair · gpt-3.5-turbo

    words related to entertainment and performers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imil
    -0.67
     descent
    -0.66
    jamin
    -0.63
     holiest
    -0.61
    installed
    -0.61
    imen
    -0.61
     prone
    -0.61
    andr
    -0.60
    yer
    -0.58
     federally
    -0.58
    POSITIVE LOGITS
     entertain
    1.20
    tainment
    1.11
     entertained
    1.05
    glers
    1.03
    eering
    0.94
    esc
    0.84
     entert
    0.83
    eers
    0.81
    Tank
    0.80
    mble
    0.80
    Act Density 0.008%

    No Known Activations