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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or movement towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lant
    -0.16
    op
    -0.16
    lara
    -0.16
    culate
    -0.16
    ue
    -0.15
    /w
    -0.15
    au
    -0.15
    íģ¼
    -0.15
    how
    -0.14
    otope
    -0.14
    POSITIVE LOGITS
    /about
    0.18
    /from
    0.18
    sgi
    0.17
    GGLE
    0.16
    sett
    0.16
    gether
    0.16
    getter
    0.15
    eriod
    0.15
    afil
    0.15
    vana
    0.15
    Act Density 0.022%

    No Known Activations