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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hos
    -0.17
    ahl
    -0.15
    ael
    -0.15
    jal
    -0.13
    hes
    -0.13
    γε
    -0.13
    ëŀį
    -0.13
     SCAN
    -0.13
    deprecated
    -0.13
    102
    -0.13
    POSITIVE LOGITS
    æĺ¯æĪij
    0.18
     below
    0.16
     follows
    0.16
    iment
    0.15
    odzi
    0.15
     Some
    0.15
     some
    0.15
    iber
    0.14
    orgia
    0.14
     attached
    0.14
    Act Density 0.022%

    No Known Activations