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

    Neuronpedia

    INDEX
    Explanations

    references to access restrictions and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    585
    -0.15
     em
    -0.15
    ooting
    -0.14
    /
    -0.14
    åĩºçīĪ社
    -0.14
    rsa
    -0.13
     needless
    -0.13
     ap
    -0.13
     reaches
    -0.13
    ż
    -0.13
    POSITIVE LOGITS
    SPATH
    0.17
    acos
    0.16
    eko
    0.15
    ÎķÎł
    0.15
    abus
    0.15
    ovit
    0.14
    év
    0.14
    elon
    0.14
     fullPath
    0.14
    ::$
    0.14
    Act Density 0.530%

    No Known Activations