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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software or product launches

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the release or introduction of something new

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cious
    -0.83
    arine
    -0.64
     wearer
    -0.61
    ottesville
    -0.61
    esthetic
    -0.60
    bered
    -0.58
     Mub
    -0.58
     Citiz
    -0.58
    ilation
    -0.58
    antry
    -0.57
    POSITIVE LOGITS
    wards
    0.84
    casts
    0.81
     invitations
    0.79
    sheets
    0.68
    fitted
    0.67
     Archdemon
    0.66
    stretched
    0.65
    posts
    0.65
    izabeth
    0.63
    dash
    0.62
    Act Density 0.031%

    No Known Activations