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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain "of" and references to specific cases or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venants
    -0.77
    urer
    -0.74
    ettlement
    -0.67
    uristic
    -0.66
    omore
    -0.64
    ocate
    -0.64
    Champ
    -0.62
     dissatisf
    -0.62
    ient
    -0.61
    erella
    -0.61
    POSITIVE LOGITS
    liest
    0.81
     Married
    0.66
     Ones
    0.63
     Osiris
    0.63
    early
    0.62
     Kosovo
    0.62
    tains
    0.61
     Jared
    0.61
    gery
    0.60
     Zub
    0.60
    Act Density 0.051%

    No Known Activations