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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific word 'anchor' and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "anchor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensation
    -0.88
    INESS
    -0.84
    enza
    -0.81
    BLE
    -0.76
    plets
    -0.72
    osponsors
    -0.70
    ensable
    -0.70
    jri
    -0.70
    axies
    -0.70
    STEM
    -0.70
    POSITIVE LOGITS
     anchor
    1.06
     anch
    1.06
     anchors
    0.96
     anchored
    0.96
    orage
    0.89
     tenant
    0.82
    ovy
    0.76
    raint
    0.74
    ments
    0.72
     Anch
    0.70
    Act Density 0.014%

    No Known Activations