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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stability or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anchor" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.82
    ensation
    -0.76
    BLE
    -0.70
    STEM
    -0.69
    orders
    -0.68
    GET
    -0.67
    osponsors
    -0.66
     Quadro
    -0.66
    tm
    -0.66
    PDATE
    -0.65
    POSITIVE LOGITS
     anch
    1.09
     anchor
    1.04
    orage
    0.99
     anchored
    0.98
     anchors
    0.90
     tenant
    0.89
    ovy
    0.80
    uckland
    0.80
    imum
    0.78
    ovies
    0.77
    Act Density 0.017%

    No Known Activations