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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mountains or physical elevation

    oai_token-act-pair · gpt-3.5-turbo

    references to mountains or related geological features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Quincy
    -0.65
    à¦
    -0.64
    period
    -0.63
    Chicken
    -0.61
    oru
    -0.61
    prints
    -0.59
    clamation
    -0.59
     Bleach
    -0.58
    sem
    -0.58
     Sharia
    -0.58
    POSITIVE LOGITS
     mount
    1.34
    mount
    1.22
     mounted
    1.17
     mounts
    1.12
    mounted
    1.11
     mounting
    0.96
    Mount
    0.94
    aint
    0.80
     showc
    0.76
     eleph
    0.75
    Act Density 0.007%

    No Known Activations