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

    Neuronpedia

    INDEX
    Explanations

    terms related to security checkpoints and physical barriers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to checkpoints in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.96
    morph
    -0.82
    mort
    -0.79
    nder
    -0.79
    cipled
    -0.79
    uscript
    -0.76
    flu
    -0.75
    nian
    -0.73
    bestos
    -0.71
    tymology
    -0.71
    POSITIVE LOGITS
     checkpoints
    1.21
     checkpoint
    1.02
     clearance
    0.90
     plaza
    0.78
     kios
    0.77
     guarding
    0.77
     manned
    0.75
     guards
    0.74
     patrol
    0.73
     keeper
    0.73
    Act Density 0.025%

    No Known Activations